cs.LG · 2026-10-19 · No. 148

Machine Learning, 2026-10-19.

73 new papers in cs.LG. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

73 entries
  1. 01

    Waiting Buys Exactly Two Moments: Endogenous Identification in Prediction-Driven Allocation

    Rama AlHamidi, Rasul Khanbayov, Erchin Serpedin, Hasan Kurban

    cs.LG

    A planner with a fixed budget of preventive help must decide whom to help and when. Waiting reveals risk but removes intervention opportunities as higher-risk individuals leave first. We characterize this tradeoff under repeated noisy signals and risk-dependent attrition: in the canonical model, a length-$τ$ observation prefix identifies exactly the latent risk moments $m_j=\mathbb E[p^j]$ for $j=0,\ldots,2τ-1$, buying two new moments per...

    arxiv.org/abs/2610.23830 · PDF

  2. 02

    CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning

    Tianmeng Hu, Biao Luo, Ke Li

    cs.LG · cs.MA

    Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational problem. We propose CocoRNA, a cooperative multi-agent reinforcement learning framework for RNA inverse design. CocoRNA simplifies the design task by decomposing it into smaller sub-problems, each solved collaboratively by multiple agents. This approach reduces the...

    arxiv.org/abs/2610.23820 · PDF

  3. 03

    Learning Personalized Memory Gating from Delayed One-Sided Feedback

    Kaixuan Ji, Zixiang Chen, Wenting Zhao, Cheng Qian, Heng Wang, Weizhi Zhang, Jielin Qiu, Liangwei Yang, Quanquan Gu,...

    cs.LG

    Long-term memory enables language-model agents to personalize future interactions, but a finite memory bank cannot preserve every extracted fact. Existing memory gating policies are typically shared across users and therefore fail to account for user-specific patterns of future reuse. In this paper, we study memory gating at the fact level. We first propose a retrieval-based labeling strategy that labels each fact by whether it is later...

    arxiv.org/abs/2610.23812 · PDF

  4. 04

    Explainable Machine Learning Analysis of Temperature Effects on Mechanical Strength of Fiber-Reinforced High-Performance Concrete

    Jagaran Chakma, Zhiguang Zhou, Badhan Chakma, Priyanta Chakma

    cs.LG

    Predicting the compressive strength of fiber-reinforced high-performance concrete subjected to temperature exposure is challenging because to the intricate interdependencies of mixture composition, fiber properties, curing conditions, and temperature. A data-driven framework to predict compressive strength utilizing 1,204 experimental records containing a diverse array of material designs and exposure situations. This study evaluates eight...

    arxiv.org/abs/2610.23811 · PDF

  5. 05

    Logic-Guided Graph Denoising Diffusion Models

    Samuel Cognolato, Luciano Serafini, Alessandro Sperduti, Andrea Cavallaro

    cs.LG

    Graph diffusion models are competitive approaches for generating complex graph-structured data. However, when such distributions have strict structural constraints, diffusion models may fail to capture them exactly, resulting in the generation of invalid graphs. In this paper, we propose a method for grounding graph diffusion models in domain-specific knowledge via First Order Logic (FOL), leveraging its expressive and interpretable formalism...

    arxiv.org/abs/2610.23766 · PDF

  6. 06

    Universal Semantic Enhancement for Weakly Supervised Anomaly Detection

    Siyu Zhou, Yuqin Xie, Hao Yuan, Yingjie Zhou

    cs.LG

    Weakly supervised anomaly detection on tabular data is an essential task in many label-scarce applications, since tabular data is widely encountered and it is commonly observed in practice that only a limited number of labeled anomalies are available alongside abundant unlabeled samples. Most existing methods try to learn features that capture the inherent distribution patterns in the target domain. However, such features often struggle to...

    arxiv.org/abs/2610.23765 · PDF

  7. 07

    LagNet: Lag-Structured Operators for Long-Term Time Series Forecasting

    Zhenan Yu, Guangxin Jiang, Jiuyun Jiang, Jin Yang

    cs.LG

    Long-term time series forecasting maps a finite history window to an extended future horizon. Many existing models focus primarily on the design of input representations and model structures, while paying less attention to the structural form of the history-to-future forecasting operator itself. We examine this operator directly and find that, across model families, sensitivity matrices exhibit recurring diagonal patterns whose diagonals...

    arxiv.org/abs/2610.23735 · PDF

  8. 08

    Escaping Parameter Space: Tight Generalization Bounds via Representation Quality

    Niclas Göring, Shuofeng Zhang, Branton DeMoss, Ard A. Louis

    cs.LG

    We derive a tight generalization bound for deterministic neural We derive a tight generalization bound for deterministic neural networks based on their last hidden layer representations. By evaluating representation quality with a parameter-free $k$-nearest-neighbor ($k$-NN) classifier, our certificate avoids traditional parameter-space complexity measures, KL divergences to a posterior, weight norms, and compression. The bound is tight:...

    arxiv.org/abs/2610.23729 · PDF

  9. 09

    Neural Expansion: A Unified Mechanism for How Deep Neural Networks Generalize

    Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino, Canlin Zhang, Xiuwen Liu

    cs.LG · cs.AI

    Deep neural networks demonstrate remarkable generalization despite being highly over-parameterized, challenging traditional statistical learning theories. While several theoretical paradigms such as margin-based bounds, PAC-Bayesian analyses, and neural tangent kernels provide global explanations, they often lack mechanistic insight into how generalization emerges from training dynamics. We introduce Neural Expansion, a unified geometric...

    arxiv.org/abs/2610.23716 · PDF

  10. 10

    Tool Recommendation for Multi-Step Agents: Finding Every Tool a Task Needs

    Sam Partee, River Stevens, Thierry Damiba, Valerie Fanelle

    cs.LG · cs.IR

    A multi-step agent task fails when a single tool it needs is missing, yet the tools an agent may need are too many to list: the roughly 8,200 tools on the platform we study have definitions that together exceed the context window of any model we evaluate. We present Tool Recommendation, a deployed system that gives an agent all of them, hundreds of times more than a typical MCP server exposes, through a fixed interface of three tools. It runs...

    arxiv.org/abs/2610.23707 · PDF

  11. 11

    Blitz: Accelerating the Diffusion Modules of AlphaFold3 and Boltz-2

    Vinay Saji Mathew, Soundar Kumara, Gretta Kellogg, William K. M. Lai

    cs.LG

    Diffusion-based protein structure prediction models produce all-atom structures in about 200 denoising steps, and that cost has driven a number of few-step samplers. We present Blitz, a few-step distillation framework that uses a geometric noise schedule to distribute steps more evenly across noise scales, then learns those updates through multistep consistency training. Physical steering and target-free candidate selection help reduce the...

    arxiv.org/abs/2610.23703 · PDF

  12. 12

    Equivalence testing and run-count design for stochastic machine-learning experiments

    Dmytro Knopov, Nadiya Shvai

    cs.LG · stat.ML

    Claims that two training methods perform equally well often rest on a non-significant difference between two or three runs per method. We develop a protocol, with its power theory, for certifying practical equivalence in per-run metrics such as the AUROC (area under the receiver operating characteristic curve). It rests on a two-level (seed x item) variance model separating between-run dispersion from item-level noise. Equivalence within a...

    arxiv.org/abs/2610.23700 · PDF

  13. 13

    TriRouter: Sparse-to-Dense Electrode-Space Routing for Robust EEG Motor Imagery Decoding

    Ying Zhou, Yaoxin, Mengting Liu

    cs.LG · eess.SP

    Motor imagery brain-computer interfaces require reliable decoding from multichannel EEG, but practical acquisition often yields sparse or corrupted electrode montages. We propose TriRouter, an electrode-space routing framework with discriminative-preservation, mask-robustness, and latent-compensation paths. A validation-calibrated router uses observable channel availability to allocate path contributions, preserving complete-channel...

    arxiv.org/abs/2610.23665 · PDF

  14. 14

    JAXtari: High-Throughput and Easy-to-Modify Arcade Learning Environment

    Quentin Delfosse, Raban Emunds, Paul Seitz, Sebastian Wette, Jannis Blüml, Daniel Kirn, Dominik Mandok, Kristian Kersting

    cs.LG

    The Arcade Learning Environment (ALE) has been a cornerstone of Deep Reinforcement Learning research, providing a standardized benchmark for evaluating general agents. However, its lack of native support for object-extraction and environment modification restricts research into evaluating whether agents learn robust causal models or rely on brittle visual heuristics. Furthermore, the ALE's dependence on CPU-based emulation creates a...

    arxiv.org/abs/2610.23650 · PDF

  15. 15

    No-Regret Language Generation

    Jiaxun Li, Vinod Raman, Ambuj Tewari

    cs.LG · stat.ML

    We introduce no-regret generation, which requires a generator to make a sublinear number of mistakes uniformly over all demonstration sequences and compatible target languages. We also formulate an agnostic variant that allows arbitrary demonstrations that may not be compatible with any languages. For both settings, we introduce tree-based mistake-forcing dimensions that exactly characterize finite-horizon minimax complexity and establish...

    arxiv.org/abs/2610.23641 · PDF

  16. 16

    Deep LLM layers expose passage-level context in EEG during silent reading

    Ingo Marquardt, Anthilia Alchanat, Priyanka Jain

    cs.LG · q-bio.NC

    In a previous report we showed that a decoder can recover open-vocabulary word-level information from 19-channel EEG recorded during silent reading, by aligning short EEG windows with hidden-state embeddings of the presented word taken from a large language model (LLM). That analysis contrasted two of the model's 33 layers: the context-free input embedding and one mid-depth layer. Here we ask how EEG-decodable structure is distributed over...

    arxiv.org/abs/2610.23638 · PDF

  17. 17

    Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition

    Juho Jung, Seongjae Kang, Jinyoung Han

    cs.LG

    Existing multi-task active learning (MTL-AL) methods predominantly rely on linear scalarization of heterogeneous objectives such as uncertainty, diversity, and gradient conflict. We argue that this entangled formulation is fundamentally limited, as linear combination fails to capture Pareto-optimal trade-offs under conflicting objectives. We propose a shift from combination to deconstruction and introduce a principled framework that rethinks...

    arxiv.org/abs/2610.23623 · PDF

  18. 18

    GRAFT-EEG: Gauge-Aware Physical Field Transport for Cross-Dataset Motor-Imagery EEG

    Ying Zhou, Mengting Liu

    cs.LG · eess.SP

    Cross-dataset EEG decoding often treats montage, reference, and active-sensor changes as representation shift, although they also alter the observation operator. We study target-statistics-blind transfer: fitting receives no target signal, label, or empirical statistic, and electrode coordinates only instantiate a fixed prediction operator. method removes the active-set common-reference gauge and transports each native mask through a template...

    arxiv.org/abs/2610.23620 · PDF

  19. 19

    ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production Planning

    Md. Mehedi Hasan Naeem, Mst. Kamrunnahar Ruma, Shakila Sultana, Nafiza Anjum, Nasreen Jannatun Nemu, Md. Sujan Ali

    cs.LG

    Staging a theatre performance requires coordinating dialogue, actor movement, stage directions, lighting focus, cue timing, and equipment constraints within the same production plan. This work presents ThetreStageAI, a retrieval augmented framework for structured Bengali theatre production planning. Rather than retrieving from one mixed corpus, the system maintains separate scene, actor-blocking, and lighting views. Bengali text is embedded...

    arxiv.org/abs/2610.23618 · PDF

  20. 20

    The Sign Code: The Hidden Binary Nature of Deep Networks

    Niclas Göring, Shuofeng Zhang, Roi Holtzman, Yoonsoo Nam, Ard A. Louis

    cs.LG

    Every neuron in a trained network outputs a number that can be separated into its sign (positive or negative) and its magnitude (absolute size). We call the set of all neuron signs the \textit{sign code}. This raises a key question: does classification depend more on the sign code or on the magnitudes? For overparameterized vision classifiers with sign-preserving activations, the answer is overwhelmingly the sign code. A $k$-nearest neighbor...

    arxiv.org/abs/2610.23616 · PDF

  21. 21

    How Many, but How Sure? Class Competition as a Confidence Proxy in Multi-Class Density-Based Counting

    Villanelle O'Reilly, Georgios Leontidis, Marc Hanheide

    cs.LG

    Multi-class density estimators can count objects in crowded scenes, but their class-wise outputs offer no indication of how reliably density mass has been allocated. We introduce a training-free confidence proxy based on local competition between the strongest class channels. The resulting prominence measure requires only the predicted density maps, with no retraining or access to model internals. We test whether residual competition is...

    arxiv.org/abs/2610.23611 · PDF

  22. 22

    When Magnitude Suffices: Reconstructing Time-Domain-Gated Microwave Signals Without Phase on a Thoracic Phantom

    Maciej Cichoń, Patrycja Gołaś, Maksymilian Bartosik, Angelika Walczak, Agata Bielecka-Dąbrowa, Maciej Ślot

    cs.LG · physics.app-ph

    Time-domain gating separates the arrivals that form a microwave S-parameter measurement. It requires the measurement of complex values, so this application almost always uses a vector network analyzer (VNA). We show that, on one calibrated measurement configuration, the gated magnitude the VNA would give can be reconstructed from a magnitude-only sweep of a spectrum analyzer with a tracking generator (SA). We select the gate center for...

    arxiv.org/abs/2610.23608 · PDF

  23. 23

    Boundary Detection for High-Dimensional Point Clouds

    Abigail Hickok, Valerio Galanti, Osama Al Dalahmah, Andrew J. Blumberg

    cs.LG · cs.CG · stat.ML

    We introduce two new methods for boundary detection in high-dimensional point cloud data, intended to work in situations with non-uniform density, high ambient dimension, and substantial noise. Our first method fits a separating hyperplane on local neighborhoods after doing local dimension reduction---this method works best when one can reliably estimate the intrinsic dimension of the data. Our second method measures the directional...

    arxiv.org/abs/2610.23590 · PDF

  24. 24

    BMuon: Budgeting Muon's Spectral Geometry for Structured Compressibility

    Rida Assalouh, Tom Jacobs, Rebekka Burkholz, Yani Ioannou, Umut Şimşekli

    cs.LG

    Muon has emerged as a strong optimizer for neural network training and admits an interpretation as steepest descent under a spectral-norm geometry. Yet we find that Muon-trained Transformers can degrade sharply when their MLP hidden channels are pruned after training. To reconcile Muon's optimization performance with structured compressibility, we introduce Budget Muon (BMuon), which modifies Muon's spectral geometry so that hidden channels...

    arxiv.org/abs/2610.23571 · PDF

  25. 25

    Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search

    Quynh Trinh, Trung Nguyen, Nam Nguyen, Tuan Dam

    cs.LG · stat.ML

    Monte-Carlo Tree Search (MCTS) typically stores only scalar mean estimates, which makes it poorly suited for tail-risk objectives such as conditional value-at-risk (CVaR). We introduce Categorical Thompson Sampling with Optimism (CATSO) and Particle Thompson Sampling with Optimism (PATSO), two distributional MCTS algorithms that maintain finite-support empirical backup laws at Q-edges. CATSO represents Q-edge laws with categorical atoms and...

    arxiv.org/abs/2610.23565 · PDF

  26. 26

    Out of Support, Not Out of Reach: In-Context Learning with Unsupported Instructions and Composed Tasks

    Xuhan Tong, Yuchen Zeng, Jiawei Zhang

    cs.LG

    In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks from a small set of input-output demonstrations, without parameter updates. Yet existing theory primarily explains ICL as identifying a latent task already represented in pretraining, leaving unclear whether ICL can succeed when either the instruction or the target task falls outside the pretraining support. We develop a theoretical framework under mild assumptions...

    arxiv.org/abs/2610.23528 · PDF

  27. 27

    Uncertainty-aware AI-enabled framework for predicting hydrogen dispersion in confined spaces to enhance operator situational awareness

    Niclas Flehmig, Mary Ann Lundteigen, Shen Yin

    cs.LG

    We present a two-stage AI-enabled framework for enhancing operator situational awareness during compressed hydrogen bunkering in maritime confined spaces. In the event of a leak, the framework first estimates the unknown leakage rate from early sensor readings and then forecasts how the hydrogen cloud will disperse over the next time steps, providing operators with a predicted concentration map together with confidence bounds. The framework...

    arxiv.org/abs/2610.23515 · PDF

  28. 28

    A Topological Signature of Learning under Noisy Labels

    Zhongtian Sun, Fan Mo, Prayag Tiwari, Kelin Xia

    cs.LG · cs.AI

    How does noisy supervision change the representations learned by a neural network? Training accuracy measures agreement with training labels but provides little information about representation geometry. We use persistent homology to track loop structure across distance thresholds in neural activations. Experiments span image classification, text classification, and modular arithmetic. On a fixed CIFAR-10/ResNet-18 training probe, equally...

    arxiv.org/abs/2610.23491 · PDF

  29. 29

    Predictable Scaling: Efficient Model Exploration via Scaling-Law Prediction

    Aishwarya Wesanekar, Sheng-Tao Yang, Jiawei Zhang, Flavio Sales Truzzi, Chen Chen, Nader Beigiparast, Shengyuan...

    cs.LG

    Evaluating candidate changes (hypotheses) to recommendation models requires full-scale training runs consuming thousands of GPU-hours, severely limiting the hypothesis space engineers can feasibly explore. We introduce Predictable Scaling (PS), a systematic framework that exploits empirically verified regularity conditions to predict full-scale model performance from small-scale proxies. PS constructs scaled-down variants via composable...

    arxiv.org/abs/2610.23453 · PDF

  30. 30

    Regularized free deconvolution for spectral repair of resampling distortion in high-dimensional particle filters

    Deming Song, Chi-Kin Lam, Kefeng Li, Hui Yu, Xilin Li, Huagang Lin

    cs.LG

    Resampling is the standard remedy for weight degeneracy in particle filters, but in high dimensions it distorts the spectrum of the ensemble covariance in a way that is computable from the importance weights. This paper studies the inverse problem: recovering the pre-resampling spectrum from the observed weights and the empirical spectrum alone, and using it without biasing the filter. We first show that the forward spectral law extends to...

    arxiv.org/abs/2610.23448 · PDF

  31. 31

    RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning

    Alexander W. Goodall, Francesco Belardinelli

    cs.LG · cs.AI

    In many real-world scenarios we need to consider formal requirements, such as safety and constraint compliance, to deploy Reinforcement Learning (RL) agents. In this paper we introduce RecReg, a safe RL framework capable of enforcing non-Markovian regular safety properties via recovery-based shielding. RecReg is a unified approach that supports different levels of a priori knowledge and safety guarantees. The paper primarily focuses on...

    arxiv.org/abs/2610.23445 · PDF

  32. 32

    Bridging Compressed Communication and Local Steps via Spectral Method in Federated Learning

    Dmitriy Bystrov, George Chirkov, Daniil Medyakov, Dmitry Bylinkin, Aleksandr Beznosikov

    cs.LG

    Federated Learning (FL) enables collaborative training of complex models across large-scale networks of edge devices while keeping data localized. However, data heterogeneity and high communication overhead remain fundamental bottlenecks. Recently, the spectral optimizer Muon has demonstrated remarkable advantages over Adam-like methods in centralized training. While recent efforts have attempted to transition Muon to FL, naive integrations...

    arxiv.org/abs/2610.23434 · PDF

  33. 33

    Residual Stochastic Concept Bottleneck Models

    Stephen Marcou, Mateo Espinosa Zarlenga, Sonia Laguna, Moritz Vandenhirtz, Julia E. Vogt, Mateja Jamnik

    cs.LG

    Concept-based models (CMs) learn human-interpretable intermediate representations that enable users to understand the model's reasoning and steer its predictions through test-time concept interventions. However, in realistic settings, their performance can be limited by concept incompleteness, where the training concepts fail to capture all task-relevant information. Adding an unconstrained residual pathway to the model's predictive process...

    arxiv.org/abs/2610.23421 · PDF

  34. 34

    Flash RNN-T: Memory-Efficient Joint Network and Transducer Loss Computation

    Mahmoud Ashraf

    cs.LG · cs.DC · cs.SD

    The recurrent neural network transducer (RNN-T) remains a practical choice for streaming speech recognition, but training requires large intermediate tensors. We present Flash RNN-T, a joint and loss implementation combining specialized kernels with optional tiled recomputation over the full alignment space and vocabulary. Tiled and untiled Flash form the entire measured throughput-memory frontier on medium and long workloads. On H100,...

    arxiv.org/abs/2610.23409 · PDF

  35. 35

    Information Estimation with Discrete Diffusion

    Alberto Foresti, Giulio Franzese, Pietro Michiardi

    cs.LG · cs.IT

    Information-theoretic measures, such as Mutual Information (MI), play a crucial role in understanding non-linear relationships between random variables and are widely used across scientific disciplines. Yet, their use on real-world discrete data remains challenging. Existing methods typically rely on embedding discrete data into a continuous space and apply neural estimators originally designed for continuous distributions. This process...

    arxiv.org/abs/2610.23404 · PDF

  36. 36

    Contracting with an Agent under Model Mismatch

    Elif Yılmaz, Jakub Tłuczek, Victor Villin, Christos Dimitrakakis

    cs.LG · cs.GT

    In the classical principal-agent setting, the principal delegates some task to the agent, who receives a payment conditioned on the outcome of the task, which in turn benefits the principal. To align their objectives, the principal designs a contract that incentivizes the agent to take actions beneficial to the principal. In practice, however, the agent may act under misspecified beliefs about the underlying environment, leading to...

    arxiv.org/abs/2610.23402 · PDF

  37. 37

    Forecasting Voltage Time Series under Anomalies Using a WGAN Model With Lipschitz Control and Progressive Kernel Critic Strategy

    Najmieh Sadat Safarabadi

    cs.LG

    In time-series forecasting tasks, the use of recursive forecasting on high-dimensional data substantially increases the complexity of the prediction process. The main challenge is that long-term dynamics becomes harder to model, since the sequences show greater temporal variability. To counteract this limitation and improve the modeling of long-term dynamics, and more importantly, address high-dimensional recursive forecasting, this paper...

    arxiv.org/abs/2610.23394 · PDF

  38. 38

    RTSM: Adapting Recursive Models to Multivariate Time-Series Classification

    Georg Tenzing, Anna Tegon, Luca Benini, Thorir Mar Ingolfsson

    cs.LG

    Accurate multivariate time-series classification requires extracting temporal features and integrating information across a sequence. Weight-tied refinement offers a way to repeatedly process these features without allocating new parameters at each stage. Applying this principle to time series requires choosing both a temporal representation and a latent-state organization suited to classification. We introduce the Recursive Time-Series Model...

    arxiv.org/abs/2610.23353 · PDF

  39. 39

    How Finite-Rank Bottlenecks Shape the Low-Rank Adaptation Landscape

    Long Nguyen-Chi, Quynh Nguyen, Thanh Nguyen-Cung, Binh T. Nguyen

    cs.LG

    Low-rank adaptation (LoRA) has become the standard method for parameter-efficient fine-tuning of large pretrained models, yet theoretical explanations for why low-rank updates suffice remain incomplete. Most existing analyses rely on the Neural Tangent Kernel (NTK) regime, which linearizes the network around the pretrained weights. In this work, we take a different approach that requires no linearization: our key observation is that, once the...

    arxiv.org/abs/2610.23343 · PDF

  40. 40

    SETAREH Transform: A Sorting-Assisted Haar-Wavelet Sparsification Method for Approximate Inner-Product Computation

    Seyed Kamaledin Setarehdan

    cs.LG

    Modern deep learning systems increasingly rely on high-dimensional vector operations, in which large input and parameter vectors are repeatedly stored, transferred, and processed. Although substantial research has focused on reducing neural-network model size through pruning, quantization, knowledge distillation, and efficient architectures, the storage, memory-traffic, and communication costs associated with repeatedly presented...

    arxiv.org/abs/2610.23338 · PDF

  41. 41

    Minimax-optimal Scaling Laws in Ridge Regression via Transfer Learning

    Yalda Shabanzadeh, Diyuan Wu, Marco Mondelli

    cs.LG · stat.ML

    Pretrained models are often reused across downstream tasks, motivating the question of whether this transfer learning procedure can provide a substantial performance improvement, namely, in terms of the scaling law. We address this question in the prototypical setting of high-dimensional regression, where (i) a pretrained \emph{source} model is trained via ridge regression, and (ii) a fine-tuned \emph{target} model is regularized via the...

    arxiv.org/abs/2610.23337 · PDF

  42. 42

    HiPredict: Predicting the missing HiRISE RED4 spectral channel with machine learning

    Ardan Suphi, Ben Moseley, Gareth S Collins, Valentin T Bickel, Vidhya G Rangarajan

    cs.LG

    The High Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter (MRO) acquires imagery of Mars at 25--30 cm/pixel, supporting studies of martian geology, climate history, and landing-site characterization. Its 14-detector focal plane assembly includes several overlapping detectors that enable the acquisition of three-channel colour-infrared images, which are important for identifying compositional variations...

    arxiv.org/abs/2610.23335 · PDF

  43. 43

    Peak-Memory Schedules You Can Trust: Exact Realization, Certified Optimality, and the Limits of Recomputation for Inference

    Ivan Fomin, Ivan Koryabkin, Boris Sheludko

    cs.LG · cs.DS · cs.PF

    Real-time inference on small devices needs low activation memory without extra latency, which makes operator order the most valuable memory lever: it is free in time. We show that the usual way of deploying a better order, handing it back to the compiler and regenerating code, is unreliable. In PyTorch Inductor the regenerated program misses its predicted peak in 22 of 54 CPU configurations. It is worse than the stock program in 9 of them and...

    arxiv.org/abs/2610.23328 · PDF

  44. 44

    Untrained CNN and coefficient-space regularization for joint reconstruction in photoacoustic tomography

    Alfio Bozi, Anwesa Dey, Souvik Roy

    cs.LG · math.OC

    The joint reconstruction of the initial pressure and spatially varying sound speed in photoacoustic tomography from boundary measurements is considered. A regularized data-driven framework is proposed in which the unknown fields are represented in finite-dimensional wavelet spaces and fixed nonlinear features generated by an untrained convolutional neural network (CNN) are used to reconstruct the initial-pressure coefficients through...

    arxiv.org/abs/2610.23315 · PDF

  45. 45

    Data-Efficient Classifier Pretraining Through Diffusion Models

    Qinyu Li, Yee Whye Teh, Chris Holmes, Joel Jaskari

    cs.LG

    Machine learning with limited data is susceptible to overfitting, especially with modern deep neural networks. Prior to the introduction of AlexNet, reconstruction-based pretraining with auto-encoder and denoising auto-encoder were found to be beneficial, partially due to the limited size of the training sets at the time. Motivated by these traditional approaches, we propose DiffPT, a simple diffusion modeling approach to pretrain a given...

    arxiv.org/abs/2610.23289 · PDF

  46. 46

    DeDiCa: A Scalable Deconfounding Discrete Causal Generative Model

    Kunchangtai Liang, Adrián Javaloy, Antonio Vergari, Isabel Valera

    cs.LG

    We introduce DeDiCa, a practical framework for efficient causal inference with discrete variables and hidden confounding that revisits classical probabilistic modeling through a tensorized parameterization of causal Bayesian networks, enabling tractable inference. Given a causal graph, DeDiCa is trained once on observational data by maximum likelihood, exactly marginalizing over hidden confounders, and can then estimate any...

    arxiv.org/abs/2610.23272 · PDF

  47. 47

    Beyond Marginal Influence: Interaction-Aware Memory Selection for LLM Agents

    BHVSP Subrahmanyam, Neeraj Choudhary

    cs.LG · cs.AI

    LLM-agent memory selection often uses retrieval rankings based on record relevance or individual influence. Such rankings cannot identify sufficient subsets under redundant or jointly necessary evidence. We study per-decision memory sufficiency: selecting a small subset that preserves full-memory behavior. To separate search error from model error, we introduce JointCoreBench, a benchmark with nine interaction families, six workflow domains,...

    arxiv.org/abs/2610.23266 · PDF

  48. 48

    ADT: All-Atom Diffusion Tokenizer for 3D Molecular Structures

    Xuantuo Huang, Encheng Su, Aoran Wang, Pan Tan, Shengyong Xu, Yizhou Wang, Chen Tang, Shixiang Tang, Mingxiao Li

    cs.LG

    Discrete structural tokenization provides a promising route to autoregressive 3D molecular generation. Yet, existing tokenizers face a trade-off between compact representation and all-atom reconstruction: atom-level tokens preserve atomic details but produce long sequences, while compact residue-level protein tokens typically omit side-chain geometry. To overcome this limitation, we propose All-atom Diffusion Tokenizer (ADT), which decouples...

    arxiv.org/abs/2610.23265 · PDF

  49. 49

    Sample, Mix, or Verify? Allocating Test-Time Compute under Imperfect Verifiers

    Srinivasan Iyengar

    cs.LG · cs.CL

    A common way to make language models and agents more accurate is to spend more compute at inference time: generate many candidate solutions and submit the one a verifier prefers. Success then requires that some candidate is correct and that the verifier picks it. The first grows predictably with the number of samples; the second does not, because real verifiers (unit tests, majority votes, LLM judges, reward models) accept wrong answers,...

    arxiv.org/abs/2610.23255 · PDF

  50. 50

    FLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded Observations

    BHVSP Subrahmanyam, Neeraj Choudhary

    cs.LG

    Restoring service after distribution-grid faults requires decisions from incomplete and conflicting information while respecting electrical constraints. Addressing this need, we introduce FLARE (Feeder-Level Agent Restoration Evaluation), a physics-grounded benchmark for post-isolation feeder restoration. FLARE con- tains 800 AC-feasible cases across five observation settings and allows agents to gather evidence, evaluate switches, and...

    arxiv.org/abs/2610.23251 · PDF

  51. 51

    Anisotropic Representation Dynamics in Transformers

    Nguyen Do, My T. Thai

    cs.LG

    Small differences between internal representations can shrink or grow as they pass through a Transformer layer, affecting how information is preserved and how sensitive the model is to perturbations. Yet it remains unclear when changes in attention weights can turn a representation difference that would otherwise shrink into one that grows. We develop a \textbf{Mixture-Gated Theory of Anisotropic Representation Dynamics} that separates...

    arxiv.org/abs/2610.23242 · PDF

  52. 52

    Response-Informed Value Estimation for Cost-Aware Multi-Turn LLM Routing

    Haotian Yan, Jiaqi Liu, Bingyi Jing, Tianjun Yao

    cs.LG

    Multi-turn LLM routing selects a model at every turn before its response is available, yet task success is revealed only when the interaction ends, leaving each intermediate choice without a label of its own. Logged trajectories, however, retain the response each call produced, which exposes what each turn required and how well the chosen model served it, evidence that outcomes alone hide. We introduce RIVET (Response-Informed Value...

    arxiv.org/abs/2610.23239 · PDF

  53. 53

    Process Reward Modeling with Reliability- and Conservatism-Aware Bayesian Belief

    Zhongjian Qiao, Zhixiang Zhou, Jiafei Lyu, Peisong Wang, Qiaosheng Zhang, Siyang Gao, Shuang Qiu

    cs.LG

    Process Reward Models (PRMs) play a central role in test-time scaling for large language model (LLM) reasoning. However, PRMs may provide inaccurate process rewards for test-time scaling, which we identify as arising from two sources of uncertainty: (1) \textit{PRM uncertainty} that arises from insufficient supervision data and imperfect PRM training; and (2) \textit{policy uncertainty} that results from the mismatch between the policy to...

    arxiv.org/abs/2610.23223 · PDF

  54. 54

    Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems

    Mohsen Amidzadeh, Lauri Viitasaari, Mario Di Francesco

    cs.LG

    Stochastic optimization (SO) plays a central role in decision-making under uncertainty. Among SO problems, time-varying stochastic optimization (TV-SO) is particularly important due to its applications in adaptive control and machine learning. Non-parametric approaches have been proposed for time-varying deterministic optimization; however, they have not been developed for their stochastic counterparts. This work addresses that gap by...

    arxiv.org/abs/2610.23204 · PDF

  55. 55

    LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization

    Hironori Ohigashi

    cs.LG · cs.AI

    Neural combinatorial optimization (NCO) rapidly produces high-quality solutions for problem structures encountered during training, but operational requirements may change after deployment and be communicated in natural language. We propose LangNCO, a framework that compiles instance-specific requirements into structured inference-time interventions for a frozen NCO solver, without changing the pretrained policy's architecture, learned input...

    arxiv.org/abs/2610.23190 · PDF

  56. 56

    A Stronger Teacher Within: Strengthening MoE Models via On-Policy Bidirectional Distillation

    Haoyu Chen, Jun Bai, Yang Liu, Jianfei Zhang, Wenge Rong

    cs.LG · cs.AI

    Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved Mixture-of-Experts (MoE) LLMs, but its outcome-level rewards provide only sparse supervision. On-Policy Distillation offers dense token-level feedback, yet requires a stronger compatible teacher, while on-policy self-distillation relies on hand-designed privileged information. We observe that the MoE architecture itself offers a way to resolve this dilemma, as...

    arxiv.org/abs/2610.23185 · PDF

  57. 57

    Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning

    Heming Zou, Qi Wang, Yixiu Mao, Yun Qu, Yuyi Guo, Zeyuan Liu, Chenglin Li, Weijie Liu, Saiyong Yang, Xiangyang Ji

    cs.LG · cs.AI · cs.CL

    Reinforcement learning with verifiable rewards has become a scalable post-training paradigm for large language models. However, training agents over long-horizon interactions presents two challenges: using only terminal rewards makes turn-level credit assignment sparse and high-variance, while sequential mini-batch updates on a fixed rollout batch introduce policy staleness as the current policy drifts from the behavior policy. Existing...

    arxiv.org/abs/2610.23181 · PDF

  58. 58

    Structural Affinity: An Algorithm for Coherent Cage-Based Shape Design

    Aviraj Newatia, Shengan Yang, Hantao Zhong, Rika Antonova

    cs.LG · cs.GR · cs.RO

    Cage-based deformation (CBD) parametrises 3D geometry through a small set of control handles, effectively enabling a variety of tasks from animation and interactive modelling to tool-based co-design, neural deformation transfer, and aerodynamic shape optimization. Many optimization approaches relying on CBD employ regularisation strategies to reduce the distortion of the deformed mesh by encouraging smooth, regular cage deformations. These...

    arxiv.org/abs/2610.23173 · PDF

  59. 59

    Nearly Linear Private Learning of Littlestone Classes

    Shay Moran, Chao Yan

    cs.LG

    Differentially private learning aims to learn from data while protecting individual training examples. For binary classification, finite Littlestone dimension characterizes approximate private PAC learnability (Alon et al., JACM 2022). Understanding how this dimension controls private sample complexity remains a central question. For classes of Littlestone dimension $d$, the first general upper bound was doubly exponential in $d$ (Bun, Livni,...

    arxiv.org/abs/2610.23160 · PDF

  60. 60

    Grounded Credit Assignment in Reinforcement Learning for Multi-Turn Search Agents

    Qirui Liu, Hao Chen, Yi Wen, Weijie Shi, Yao Zhao, Xianhe Chen, Hao Zhao, Xing Tang, Weihong Luo, Yuyu Luo

    cs.LG

    Outcome-reward reinforcement learning such as GRPO gives every token of a search-agent rollout the same advantage, although the rollout exercises two capabilities: finding evidence and using it. We show that accuracy improves without grounding: Search-R1 raises accuracy on all seven QA benchmarks, yet on Bamboogle the evidence-supported share of correct answers falls from 84.0% to 42.9%. We attribute this to GRPO's credit assignment: rollouts...

    arxiv.org/abs/2610.23148 · PDF

  61. 61

    Local proxies for memory-efficient training

    Wu S. Zihan, Brian A. Yuan, Guillaume Bellec

    cs.LG · cs.AI

    Local learning algorithms can reshape resource requirements of artificial intelligence. The memory bottleneck of standard end-to-end backpropagation lies in the need to store all network activations until the loss gradient has been propagated back through. Local learning avoids this, but typically at a cost in accuracy. We study how to achieve accurate and memory efficient local learning in transformers. For each transformer block, we train a...

    arxiv.org/abs/2610.23145 · PDF

  62. 62

    MetaCurate: Evolving Curation Filters for High-Quality Agentic Coding Data

    Donghoon Kim, Seunghyuk Oh, Kevin Galim, Minseo Kim, Minjae Lee, Younghyun Kim, Wooseok Seo, Hyung Il Koo, Wonjun Kang

    cs.LG

    Supervised fine-tuning on agent trajectories is an effective way to improve coding agents, but selecting useful training examples requires more than identifying successful runs. A resolved patch may follow inefficient reasoning or unnecessary tool use, while a failed run may still contain useful intermediate steps. Training pipelines therefore rely on rules and qualitative assessments to filter trajectories, yet designing these filters...

    arxiv.org/abs/2610.23134 · PDF

  63. 63

    LED: Improving Masked Diffusion Language Models by Lookahead Editing

    Yuyan Zhou, Zeyuan Yang, Yuxuan Song, Zhicheng Cai, Hongli Yu, Weiying Ma, Hao Zhou, James Kwok

    cs.LG · cs.CL

    Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive language models, enabling non-autoregressive text generation through parallel decoding. Existing dLLMs can be broadly categorized into two families: masked diffusion models (MDMs) and uniform diffusion models (UDMs) In this work, we theoretically show that MDMs are easier to optimize due to their mask-based transition schedule but have lower...

    arxiv.org/abs/2610.23122 · PDF

  64. 64

    Domain-specific language alignment of multimodal embeddings towards explainable predictions

    Gabrielė Tijūnaitytė, Thijs L. van der Plas, Mohamed-Bachir Belaid, Rob Knapen, Maciej J. Soja, Ioannis N. Athanasiadis

    cs.LG · cs.CV

    Multimodal data are commonly fused into latent representations that improve downstream task performance but are not interpretable, limiting their application in domains that require explainable model decisions. Vision-language alignment has made image embeddings interpretable through language, but requires vast image-caption training data. However, captioned data are typically not available for multimodal embeddings, as relevant features...

    arxiv.org/abs/2610.23110 · PDF

  65. 65

    Towards a GraphNARX model for structural dynamics

    George Tsialiamanis, Keith Worden

    cs.LG

    The current paper introduces the GraphNARX model, a graph-based nonlinear autoregressive exogenous model for structural dynamics. The model is built to account for the geometry of structures and to model dynamic behaviour as the interaction between elements of the structure. Similar to other types of NARX models, GraphNARX is used for system identification. Nodal attributes of the graph encode past displacements and nodal forces, and the...

    arxiv.org/abs/2610.23103 · PDF

  66. 66

    Where Latents Belong and How They Flow: Joint Identification of Structural Roles

    Xintong Li, Kun Zhang, Yujia Zheng

    cs.LG

    Latent factors in dynamical systems can play different roles across observations and time. For example, an idea in a group meeting may be expressed by only some participants, inherit information from earlier discussions, and shape what is said next. We formalize this notion as the structural role of a latent factor, describing where it is expressed, whether it receives influence from the past, and whether it transmits influence to the future....

    arxiv.org/abs/2610.23074 · PDF

  67. 67

    Path to Prior-Data Fitted Relational Models via Learned Latent Multi-table Representations

    Mohammad Sadeq Abolhasani, Viswanath Ganapathy

    cs.LG · cs.AI

    Prior-data fitted networks (PFNs) show that pretraining on large populations of synthetic tasks can enable generalization to unseen datasets with little or no downstream fine-tuning. This paradigm is effective for transformer-based tabular and relational foundation models such as RDB-PFN, but remains largely unexplored for graph-based relational models built on message passing. We pretrain the graph-based relational foundation model Griffin...

    arxiv.org/abs/2610.23073 · PDF

  68. 68

    GR-OPD: Group-Relative Sequence Credit for On-Policy Distillation

    Yushu Wang, Renkai Yang, Jingcao Xu, Zili Geng, Haihong Tang, Yaohui Jin, Hao He

    cs.LG

    On-policy distillation (OPD) provides token-level teacher feedback, yet common sampled-token updates assign credit locally and omit the effects of earlier actions on subsequent feedback. We introduce \method{} (Group-Relative On-Policy Distillation), which decouples feedback computation from credit assignment by aggregating token feedback into calibrated sequence-level credit. We establish a theoretical basis for this approach by showing...

    arxiv.org/abs/2610.23042 · PDF

  69. 69

    Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design

    Benhao Huang, Chufan Shi, Junlin Chen, Shicheng Wen, Zhengzhong Liu, Eric Xing, Xuezhe Ma

    cs.LG

    Looped language models reuse physical Transformer blocks across logical depth, but established architectures entangle recurrence placement, input injection, and recurrent state organization. We isolate these axes in models trained from scratch at matched parameter scale, logical depth, and token budgets, and then test whether the resulting design principles transfer to resident- and active-parameter-matched Mixture-of-Experts (MoE) models....

    arxiv.org/abs/2610.23036 · PDF

  70. 70

    "Deep lifts": Neural networks can generalize even with the dumbest optimizer

    Sunil Madhow, Yu-Xiang Wang

    cs.LG

    Given a labeled dataset $\{(x_i, y_i)\}_{i = 1}^n$, consider drawing a parameter vector $\hatθ$ uniformly at random from those that interpolate the data within a width-$W$ depth-$D$ ReLU architecture with continuous weights bounded within $[-M, M]$. We study the generalization properties of $\hatθ$ in the case where the dataset can, in fact, be explained by a smaller $w$-by-$d$ ReLU network. Despite the obliviousness of the selection rule for...

    arxiv.org/abs/2610.23009 · PDF

  71. 71

    A Minimal ReLU Classifier on Non-Linearly Separable Data: Convergence and Implicit Bias at and beyond the Edge of Stability

    Quan Nguyen, Robin Yadav, Param Mody, Mark Schmidt

    cs.LG

    Gradient descent (GD) with large learning rates can successfully optimize neural networks even though classical smoothness-based learning rate conditions are violated. Yet theory for this regime largely covers linear models or linearly separable data. We analyze a minimal setting outside both regimes. Specifically, a two-neuron ReLU network trained with logistic loss on 1D non-linearly separable data. The objective is nonconvex and nonsmooth,...

    arxiv.org/abs/2610.23007 · PDF

  72. 72

    A Label Noise Robust Algorithm for Graph Data using Neighborhood Label Distribution

    Pintu Kumar, Nandyala Hemachandra

    cs.LG · cs.AI · math.ST

    Graph Convolutional Networks (GCNs) have demonstrated exceptional performance on graph-structured data. However, their success heavily relies on the availability of clean labels, an assumption that often fails in real-world scenarios. The learnability of GCNs is intrinsically linked to the neighborhood structure of nodes, making it critical to understand how this structure changes in the presence of label noise. In this work, we investigate...

    arxiv.org/abs/2610.22998 · PDF

  73. 73

    TALLOP: Joint Optimization of Local Training and Communication Compression for Time-Constrained Federated Learning

    Honoka Anada, Yafei Ou, Shinya Takamaeda-Yamazaki

    cs.LG · cs.DC

    Minimizing the wall-clock time required to reach a target accuracy is crucial in federated learning (FL), where many applications require frequent model updates as data distributions evolve over time. Nevertheless, in heterogeneous environments, slow clients with limited computational and communication capabilities can delay global synchronization, forcing faster clients to wait and increasing the overall training time. To mitigate this...

    arxiv.org/abs/2610.22996 · PDF

This edition is part of The Daily Abstract — cs.LG archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.