cs.LG · 2026-07-11 · No. 50
Machine Learning, 2026-07-11.
60 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
60 entries-
01
SLORR: Simple and Efficient In-Training Low-Rank Regularization
David González-Martínez, Shiwei Liu
cs.LG · cs.AI
Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable to aggressive factorization without significant accuracy loss. Existing training-time low-rank regularizers can improve compressibility, but they often require SVDs of large weight matrices, modify the model architecture (introducing additional trainable parameters), or rely on stateful cached quantities. To address these...
-
02
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
Duen Horng Chau, Donghao Ren, Fred Hohman, Dominik Moritz
cs.LG · cs.AI · cs.DS · cs.HC
While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the rich k-nearest-neighbor (kNN) graph that UMAP constructs internally. This graph encodes the data manifold in its original high-dimensional space, before the distortion that UMAP's 2D projection introduces. We demonstrate the untapped potential of this internal representation, showing how standard...
-
03
Super Weights in LLMs and the Failure of Selective Training
Shreyas Subramanian, Adewale Akinfaderin, Akarsha Sehwag
cs.LG
Recent work identified Super Weights, individual parameters whose removal degrades model performance by orders of magnitude. We show that this degradation due to pruning Super Weights does not universally apply to all LLMs. Furthermore, if these parameters are so important, Super Weight-aware training should be effective. We show the opposite. Training Super Weights in isolation (100 to 8,192 parameters) drops accuracy to random-guessing...
-
04
Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference
Chuning Zhu, Eva Xu, Jose Barreiros, Krishnan Srinivasan, Paarth Shah, Abhishek Gupta
cs.LG · cs.RO
Human decision-making is highly flexible -- some actions are taken immediately; others require longer deliberation. Language models have exhibited a similar capacity for adaptive "reasoning." However, transferring this capability to continuous control policies has been challenging, as directly reasoning in language space may lack the granularity for spatial understanding and precise motions. In this work, we show that reasoning for control...
-
05
Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems
Emmanouil Kavvousanos, Francky Catthoor, Vassilis Paliouras
cs.LG · eess.SP
Narrowband interference (NBI) severely degrades orthogonal frequency-division multiplexing (OFDM) systems by corrupting subcarriers and rendering classical soft demodulation ineffective. Conventional compressed-sensing (CS) mitigation exhibits high sequential latency and leaves structured, non-Gaussian residuals that cause log-likelihood ratio (LLR) unreliability, decoder saturation, and severe error floors when employing classical Gaussian...
-
06
MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph Reinforcement Learning
Harrison Rush, Vincent Davis, Simone Antonelli, Vikash Singh, Jesse Shrader, Emanuele Rossi
cs.LG
We address liquidity placement in the Bitcoin Lightning Network (LN): given a fixed budget, which channels should a node open to maximize its routing capacity? We cast this as a budget-constrained combinatorial optimization problem on graphs, selecting $k$ edge additions that maximize $s$--$t$ max-flow, a theory-grounded measure of routing capacity, and solve it with graph reinforcement learning. Our lightweight agent combines a...
-
07
A Practical Investigation of Training-free Relaxed Speculative Decoding
Guoxuan Xia, Luka Ribar, Paul Balanca
cs.LG · cs.AI
Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its rejection and resampling steps exactly preserve the LLM's sampling distribution. Recent work argues that relaxing this strict guarantee can yield further speed-ups, controlled capability-speed trade-offs, or even capability gains....
-
08
Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models
Teng-Ruei Chen
cs.LG
Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle. Recent analysis shows that test-time resampling can recover per-instance selection headroom that no single-commit router captures; however, that guarantee holds only under an idealized oracle equipped with correctness labels and an unconstrained budget, neither of which a...
-
09
EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy
Wenxiu Ding, Muzhi Liu, Zheng Yan, Mingjun Wang, Yifan Zhao, Qiao Liu
cs.LG
Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information. To satisfy edge-level differential privacy, a common approach is to inject noise into all elements of the graph's adjacency matrix, thereby obfuscating the existence of any single edge. However, stronger privacy requires more...
-
10
Secure Decentralized Federated Learning via Gossip and Virtual Voting
Amirhossein Taherpour, Xiaodong Wang
cs.LG · cs.DC
Decentralized federated learning (DFL) removes the central server by letting nodes exchange model updates through peer-to-peer gossip, but existing gossip-based methods often lack provenance finality and resilience to Byzantine or lazy participants. Ledger-assisted federated learning (FL) improves auditability, yet blockchains, shards, or settlement committees can reintroduce global coordination costs that conflict with DFL locality. This...
-
11
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
Ali Larian, Qian Lin, Chang Zong Wu, Daniel S. Brown
cs.LG · cs.AI
As autonomous agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such changes rather than overfitting to any single environment. Inverse reinforcement learning (IRL) provides a principled way to infer such objectives from human feedback. However, existing analyses of optimal teaching approaches for IRL focus on single-environment,...
-
12
BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression
Yuantian Shao, Peisong Wang, Zhilei Liu, Chuangyi Li, Yuanteng Chen, Pengcheng Xie, Yiwu Yao, Zhihui Wei, Jian Cheng
cs.LG
Large language models (LLMs) are increasingly constrained by memory capacity, weight bandwidth, and checkpoint storage during deployment. Existing low-bit compression methods mainly follow two directions. Scalar or group-wise quantization is simple and compatible with efficient low-precision kernels, but its representation capacity becomes limited when the target budget approaches 2 bits per weight. Vector-quantized weight compression...
-
13
Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence
Yann Claes, Pierre Geurts, Vân Anh Huynh-Thu
cs.LG
Over the last few years, there has been an increased interest in making machine learning models more interpretable. Although a great deal of effort goes into developing techniques for interpreting the interactions learned by a given model, fewer studies focus on assessing the quality of such explanations. Even fewer focus on how to adjust the model to produce explanations faithful to prior knowledge, a process known as explanation-guided...
-
14
Federated Deep Learning for Privacy-Preserving Cardiovascular Disease Risk Prediction
Hyunho Mo, Djura Smits, Mahlet A. Birhanu, Maarten J. G. Leening, Daniel Bos, Pim van der Harst, Esther E. Bron
cs.LG · cs.HC
Cardiovascular disease risk prediction models often rely on data from a single institution or centrally pooled datasets. Extending these models across institutions could be limited by privacy regulations and constraints on sharing patient-level data. Federated learning enables collaborative model development without transferring sensitive patient data, but its application in healthcare remains challenging because datasets often differ in...
-
15
Robust Bayesian Decision Making under Adversarial Uncertainty
Haripriya Harikumar, Sammie Katt, Yasir Zubayr Barlas, Samuel Kaski
cs.LG
Scientific experiments are often designed to maximize information gain, yet in many applications the primary objective is to support reliable downstream decision-making. Existing decision-aware experimental design and active learning methods typically assume well-specified outcome models and implicitly rely on the stability of the optimal decision under real-world perturbations. In practice, however, experimental outcomes are frequently...
-
16
Spectral Stability of Pseudoinverse-Based Extreme Learning Machine
Bich Van Nguyen, Ngoc Anh Khong
cs.LG · math.SP
Extreme Learning Machine (ELM) computes output weights analytically using the Moore-Penrose pseudoinverse. Although this leads to fast training, its numerical stability depends strongly on the conditioning of the hidden layer matrix. This paper studies pseudoinverse-based ELM from a spectral perspective. We show that the smallest singular value governs perturbation amplification in the output weights, while the condition number provides a...
-
17
Contravariance Theory: Strong Alignment for Minimal Solutions to Hard Tasks
Dan Yamins, Aran Nayebi
cs.LG · q-bio.NC
A series of results from the NeuroAI over the past fifteen years have raised core questions both about how to compare Deep Neural Network (DNN) models to the brain, and about how much convergent evolution to expect between artificial networks and real brain networks. Here, we show that for any two minimal DNN solutions to a sufficiently hard task: (i) "weak" alignment of network representations based on affine mappings guarantees "strong"...
-
18
CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency
Xin Wang, Yunshi Wen, Yanan He, Haotian Xu, Youlan Zhao, Michel Ferreira Cardia Haddad, Tengfei Ma
cs.LG
The operational integrity of complex industrial systems relies on precise anomaly detection and diagnosis. The vast majority of existing methods narrowly focus on capturing temporal similarities of representations, often overlooking the disruption of internal causal relationships, which characterizes system failures and latent anomalies. In this paper, we propose a novel framework (CAAD) that reframes anomaly detection as the continuous...
-
19
Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Data
Ofir Arviv, Kristjan Greenewald, Yotam Perlitz, Hadar Mulian, Michal Shmueli-Scheuer, Leshem Choshen
cs.LG
The inherent rigidity of fixed-size benchmarks makes them an inefficient tool for model evaluation. Diverse evaluation objectives, including model ranking, model selection and testing throughout development, demand varying levels of statistical power. The mismatch between fixed sample sizes and these diverse needs results in either excessive computational cost or compromised reliability - a critical concern for model evaluation. To overcome...
-
20
Systematic Evaluation of Learning Rate Scheduling Strategies Across Heterogeneous Architectures
Hafsa Mateen, Radu Timofte, Dmitry Ignatov
cs.LG · cs.CV
Choosing a learning rate scheduling strategy is critical to neural network training, but manual selection is costly and rarely exhaustive. While classical AutoML approaches often treat the scheduler as a secondary hyperparameter, we systematically investigate its impact on classification accuracy across a diverse pool of architectures. We evaluated 30 representative architectures from convolutional and transformer families within the LEMUR...
-
21
Ensemble Diversity Optimization for Subjective Supervision
Xia Cui, Ziyi Huang, N. R. Abeynayake
cs.LG · cs.CL
Subjective NLP tasks often exhibit systematic annotator disagreement, requiring models that represent uncertainty rather than collapse it. We introduce Ensemble Diversity Optimization (EDO), a prediction-space framework that jointly optimizes ensemble weights, effective cardinality, and calibration through a unified differentiable objective. EDO learns ensemble composition and size end-to-end via Gumbel-Softmax relaxation and incorporates a...
-
22
Frequency-Domain Multi-Modality Transportation Modeling
Jiewen Deng, Hangchen Liu, Junchen Li, Boyuan Zhang, Renhe Jiang
cs.LG
Multi-modality transportation refers to urban systems composed of multiple transportation modes, such as traffic flow and public transit, whose dynamics are coupled by shared temporal patterns. Accurate multi-modality transportation forecasting remains challenging because (1) different modalities exhibit distinct spectral characteristics and (2) interact unevenly across frequencies, whereas most existing methods operate primarily in the time...
-
23
MatBind: A Shared Embedding Space for Multimodal Materials Characterization
Le Yang, Anoop K. Chandran, Jona Östreicher, Evgenii Sovetkin, Adrian Mirza, Sebastien Bompas, Bashir Kazimi, Pascal...
cs.LG
Fully characterizing a crystalline material requires integrating heterogeneous data sources -- atomic structures, diffraction patterns, electronic density of states, and natural language -- each of which captures a different facet of the same physical object. In practice, however, these modalities are stored and analyzed in isolation, making it difficult to relate or query materials across representational boundaries. We present MatBind, a...
-
24
Predicting Male Fertility Using Machine Learning: A Semen Parameters Based Analysis with the VISEM Dataset
Shahnawaz Qureshi, Raja Khurram Shahzad, Muhammad Fozan, Emal Kawal, Syed Aziz Shah, Sattam Al-Anazi, Syed...
cs.LG · cs.AI
Male infertility is a significant yet often underdiagnosed aspect of reproductive health, with semen analysis serving as the cornerstone of clinical evaluation. To address this problem, this study investigates the use of machine learning algorithms to classify male fertility status based on key semen parameters, i.e., sperm concentration, motility, and morphology, using the VISEM dataset. This dataset includes semen samples from 85...
-
25
Beyond Backpropagation: Monte Carlo Method Can Train Deep Neural Networks
Hong Zhao
cs.LG · stat.ML
Backpropagation (BP) dominates deep learning training, but its reliance on gradients brings inherent troubles -- vanishing and exploding gradients. The pursuit of gradient-free methods has long been a goal in the field of artificial intelligence. This paper shows that indeed the simplest Monte Carlo algorithm implemented on a single GPU -- randomly mutate a parameter, keep it if the loss decreases, otherwise retry -- can practically train...
-
26
Dynamics of Gradient Descent with Large Step Size Near a Manifold of Flat Minima
Lachlan Ewen MacDonald, René Vidal
cs.LG · math.DS · math.OC
An important quantity in the theory of gradient descent (GD) is the \emph{sharpness}, defined as the largest eigenvalue of the objective Hessian. Classical analyses typically require the step size to be uniformly smaller than twice the reciprocal of the sharpness, but this condition is frequently violated in the training of deep neural networks. Recent work bridges this gap in the setting of overparametrised least-squares with a \emph{single...
-
27
Eigenvalue Calibration for Semantic Embeddings of Large Language Models
Sebastian G. Gruber, Nassim Walha, Francis Bach, Florian Buettner
cs.LG
Uncertainty quantification is central to the reliable deployment of large language models (LLMs), and eigenvalues of semantic embeddings have recently emerged as a key tool in state-of-the-art methods. However, conventional calibration results developed for classification probabilities cannot be directly transferred to eigenvalues. We address this gap by proposing a novel framework for calibrating the eigenvalues of semantic embeddings. We...
-
28
Self-Adaptive Anomaly Detection with Reinforcement Learning and Human Feedback in Connected Vehicles
Matthias Weiß, Athreya Hosahalli Prakash, Maurice Artelt, Falk Dettinger, Nasser Jazdi, Michael Weyrich
cs.LG · cs.AI
Connected vehicles are autonomous cyber-physical systems whose behavior must be continuously monitored during operation to detect deviations from normal operation before they propagate into failures. Such evaluation is challenging because the systems themselves evolve: over-the-air updates, configuration changes, and shifting workloads alter the definition of normal behavior, causing static diagnostic methods to degrade silently over time....
-
29
Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability
Amir Asiaee
cs.LG
Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one. These experiments are usually summarized by a point estimate, even though the evaluation may be monitored while it runs or adapted toward suspected failures. This makes it hard to tell whether a reported fidelity or patching effect is a...
-
30
Spectral Analysis of Dueling Q-Learning
Donghwan Lee
cs.LG · cs.AI
Q-learning is a fundamental algorithm in reinforcement learning (RL) for solving discounted Markov decision processes (MDPs) when the transition kernel is unknown. The deep Q-network (DQN) extends Q-learning by using a deep neural network for Q-function approximation, which makes Q-learning applicable to more practical high-dimensional problems. Dueling Q-learning decomposes the Q-function into a value function and an advantage function and...
-
31
AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
Siyuan Wen, Jiahao Zeng, Ningning Ding
cs.LG · stat.ML
Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models. Current diffusion unlearning techniques determine the model update direction by either using alternatives of the target concept as an anchor or using empty prompts. The anchor-based method relies on manually and semantically-chosen anchors that risk biased unlearning, while the anchor-free method inherently suffers from...
-
32
ArtMine: Discovering and Formalizing Artistic Processes
Kaustubh Kumar, Ashutosh Ranjan, Vivek Srivastava, Blessin Varkey, Shirish Karande
cs.LG · cs.AI
Understanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape artistic production. While recent generative AI systems can synthesize artworks with high fidelity, they primarily model distributions over finished artifacts rather than the creative processes underlying their creation. In practice, artistic workflows are only partially documented through...
-
33
Write-Protected Discrete Bottlenecks for Language-Grounded World Models: A Structural Limitation and Sufficient Fix
Jiayi Fang
cs.LG
How should language interface with a world model's discrete symbol system? The dominant paradigm -- end-to-end injection of LLM/VLM features into robot world models (RT-2, Octo, PaLM-E) -- implicitly assumes that language gradients can directly shape physical symbol representations. We ask whether this assumption is safe, find that it is not, and characterize the minimal architectural constraint that prevents the failure. Any language...
-
34
Learning $\mathsf{AC}^0$ under Locally Sampleable Graphical Models
Weiming Feng, Xiongxin Yang, Yixiao Yu, Yiyao Zhang
cs.LG · cs.DS
The problem of learning constant-depth circuits holds profound implications for computational learning theory. In a seminal result, by introducing the low-degree algorithm, Linial, Mansour, and Nisan (J. ACM 1993) presented a quasipolynomial-time learner for $\mathsf{AC}^0$ under the uniform distribution. However, obtaining comparable learning guarantees for broader classes of correlated distributions has remained a longstanding challenge....
-
35
Classifier Chain-based Pathological Test Recommendation
Abu Rafe Md Jamil, Nayan Malakar
cs.LG
Accurate and timely diagnoses are essential for quality patient care. However, delayed recommendation of diagnostic tests and physicians' subjective interpretations can hinder effective care. This study introduces a pathological test recommendation system that speeds up the test selection process using patient symptoms before physician consultation. The recommendation task is framed as a multi-label classification problem utilising the...
-
36
CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation
Sai Spandana Chintapalli, Pratik Chaudhari, Christos Davatzikos
cs.LG
Quantifying variability in a target population relative to a reference population is central to many scientific and clinical problems (e.g., diseased vs. healthy). Yet, without paired data and in the presence of heterogeneous target variation, existing methods struggle to separate multiple modes of target-specific variation. We propose \textit{CASL-VAE}, a deep contrastive latent variable model that learns structured latent generative factors...
-
37
An interpretable Good--Turing restart criterion for k-means++
Renato Cordeiro de Amorim
cs.LG · stat.ML
The k-means++ algorithm is commonly restarted multiple times to avoid poor local optima, yet the number of restarts is almost always chosen arbitrarily and applied uniformly regardless of data set difficulty. This undermines any comparison relying on such a choice and wastes computation on easy data sets while potentially under-serving hard ones. We introduce GTRC, a restart criterion combining a Good-Turing estimate, a proven unconditional...
-
38
Structure Learning on Clustered Data
Ryan Thompson, Matt P. Wand, Veerabhadran Baladandayuthapani
cs.LG · stat.ME · stat.ML
Recent algorithmic advances have made directed acyclic graph (DAG) structure learning scalable for causal discovery. Yet, the currently available techniques assume a completely homogeneous population, precluding their application to clustered data where cluster-specific variations (e.g., patient-specific effects) are common. We address this issue by introducing a new approach that estimates a global structure while accounting for local...
-
39
RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting
Sumit Satishrao Shevtekar, Chandresh Kumar Maurya
cs.LG · cs.AI
Real-world time series exhibit complex dynamics characterized by multiple simultaneous temporal patterns: short-term fluctuations, periodic seasonal cycles, long-term trends, and irregular abrupt changes. However, many existing forecasting architectures rely on single-path temporal modeling--transformers capture long-range dependencies but smooth local variations, convolutions capture local patterns but have limited receptive fields, and...
-
40
PIT-SUN: A Deployable Empirical Marginal Transform Framework with Expectation-Consistent Recovery for Regression in Recommender Systems
Mingyu Zhao, Zhaohan Li, Zhenxiong Miao, Xu Zhang, Dewei Leng, Yanan Niu, Kun Gai
cs.LG
Estimating original-space conditional expectations is central to value-driven recommender systems, including dwell time, GMV, and LTV forecasting. Standard MSE is expectation-consistent in principle, but its gradients become unstable on heavy-tailed, zero-inflated, and multimodal targets, causing mean collapse and tail shrinkage. Target transformation alleviates this scale conflict, yet any useful nonlinear marginal transform loses...
-
41
Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs
Lorenzo Pantè, Andrea Fanti, Roberto Capobianco
cs.LG · cs.AI
Open-ended curricula in Reinforcement Learning (RL) aim to train generally-capable agents by identifying tasks that facilitate learning increasingly complex skills. A major challenge when designing such curricula is assessing task difficulty relative to the agent's current learning progress. While previous work has explored using scalar task scores or textual summaries of the agent's behavior, here we study a different approach: directly...
-
42
Understanding Layer Patching in Model Size Interpolation
Sara Kangaslahti, Jonathan Geuter, Nihal V. Nayak, Marco Fumero, Francesco Locatello, David Alvarez-Melis
cs.LG
Zero-shot model size interpolation aims to create new models of intermediate target sizes by combining existing models without additional training. Recent work on boomerang distillation [Kangaslahti et al., 2026] shows that a student language model distilled from a larger teacher can be expanded by iteratively patching its layers, replacing student layers with contiguous blocks of teacher layers to obtain models whose size and performance...
-
43
DeepPySR -- A Symbolic Regression Framework with Dynamic Pruning, Pareto Selection, and Hierarchical Composition for Real-World Scientific Discovery
Fuling Chen, Kevin Vinsen, Phillip Melton, Rae-Chi Huang
cs.LG
Symbolic regression (SR) discovers analytical equations from data, yielding glass-box models with directly interpretable formulas, unlike black-box methods that rely on unstable post-hoc tools such as SHAP or LIME. This transparency is crucial in clinical medicine and social science, but SR faces three challenges: high-dimensional inputs, principled selection of Pareto-front formulae, and data irregularities such as multicollinearity and...
-
44
Workload-Preserving Differentially Private Synthetic Data for Causal Inference via Maximum-Entropy Calibration
Amir Asiaee, Kaveh Aryan
cs.LG
Workload-based differentially private (DP) synthetic data methods privately measure aggregate queries and post-process the noisy answers into synthetic records. Generic workloads can achieve strong distributional fidelity, but causal estimands such as the average treatment effect (ATE) depend on treatment-arm balance and outcome moments that generic marginals need not preserve. We propose causal workloads: DP query sets designed around the...
-
45
Contrastive Order Learning: A General Framework for Ordinal Regression
Chaewon Lee, BeomJun Shim, Kwang Pyo Choi, Chang-Su Kim
cs.LG
We propose contrastive order learning (ConOrd), a contrastive learning framework for ordinal regression that integrates the strengths of contrastive learning and order learning. While contrastive learning effectively leverages all samples in a batch, it typically ignores the inherent ordering among rank labels. Conversely, order learning explicitly models label ordinality but often relies on local, margin-based comparisons, limiting its...
-
46
Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization
Ryusei Yamada, Naoki Sato, Hideaki Iiduka
cs.LG
Stochastic gradient descent (SGD) is a cornerstone of modern optimization. While its performance under heavy-tailed noise is often addressed through specialized modifications such as gradient clipping or normalization, we investigate a more fundamental question: how does vanilla SGD, particularly with momentum, perform in the presence of heavy-tailed noise? In this paper, we refine existing convergence results for vanilla SGD and, more...
-
47
Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data
Chaewon Lee, Seon-Ho Lee, Chang-Su Kim
cs.LG
Rank estimation under label noise poses a fundamental challenge, as ordinal annotations often exhibit structured uncertainty rather than simple label corruption. In this paper, we reformulate rank estimation with noisy ordinal labels as a stochastic ordering problem, in which each instance is inherently associated with multiple plausible ranks instead of a single deterministic label. Based on this view, we propose stochastic order learning...
-
48
Deep Learning Method for Stationary Distribution of Reflected Brownian Motion
Jim Dai, Zhanhao Zhang
cs.LG · cs.AI
The stationary distribution of reflected Brownian motion (RBM) plays an important role in the analysis of high-dimensional stochastic systems, yet closed-form solutions are known only for a few special cases. Computing important performance metrics, such as tail probabilities, is even more intractable, despite their practical relevance. In this paper, we develop a deep learning approach that accurately and efficiently learns the Laplace...
-
49
Modular Pretraining Enables Access Control
Ethan Roland, Murat Cubuktepe, Erick Martinez, Stijn Servaes, Keenan Pepper, Mike Vaiana, Diogo Schwerz de Lucena,...
cs.LG
AI developers face a dual-use dilemma. An AI capability that helps one user cure a disease can help another synthesize one. This dilemma could be resolved with access control, limiting dual-use AI capabilities to trusted deployments with a legitimate need. A gold standard for access control would be to serve separate models with different capabilities to different users. However, training and deploying multiple models is prohibitively...
-
50
Cross-Modal Generative Framework for Signal Translation from Fetal-Maternal Electrocardiograms to Fetal Doppler Waveforms
Tongli Su, Alireza Rafiei, Marly van Assen, Reza Sameni, Gari D. Clifford, Faezeh Marzbanrad, Nasim Katebi
cs.LG · eess.SP
Fetal electrocardiogram (fECG) and Doppler ultrasound provide complementary views of fetal cardiovascular function: fECG captures electrical activity while Doppler reflects mechanical hemodynamics shaped by factors such as placental resistance and vascular compliance. Understanding the recoverable and unrecoverable Doppler components through reconstruction from fECG offers insight into the relative contributions of electrical versus...
-
51
When Thinking Hurts: Epistemic Signals in the Reasoning Chains of Visual Language Models
Mayank Singal
cs.LG · cs.AI
Uncertainty quantification for visual language models (VLMs) conventionally targets the answer token distribution. We provide the first three-family empirical characterisation of answer entropy behaviour in thinking-mode VLMs. Running four models on identical POPE adversarial samples, we find three qualitatively distinct patterns: Qwen3-VL-8B-Thinking shows complete collapse (ans H AUROC = 0.492); GLM-4.1V-9B-Thinking shows no collapse...
-
52
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
Jiantong Jiang, Peiyu Yang, Rui Zhang, Feng Liu
cs.LG · cs.AI · cs.CL
Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In this survey, we focus on system-aware KV infrastructure for serving LLMs (abbreviated as sKis). We revisit recent work from a system behavior perspective, organizing...
-
53
Reinforcing the Generation Order of Multimodal Masked Diffusion Models
Yidong Ouyang, Zhe Wang, Sourav Bhabesh, Dmitriy Bespalov
cs.LG · cs.AI · stat.ML
Diffusion Language Models (DLMs) have recently achieved substantial progress in natural language generation tasks. Recent research demonstrates that adaptive token generation ordering can significantly improve performance in mathematical reasoning and code synthesis applications. In this work, we investigate the optimization of generation order for both text-to-image synthesis and multimodal understanding. We first establish that, unlike...
-
54
Who Analyses the Analyser? Self-Validating LLM Hazard Analysis with Constitutional Meta-STPA
Samuel Tetteh, Udip Shrestha, Joshua R. Waite, Cody Fleming
cs.LG · cs.AI
Large language models (LLMs) are increasingly trusted to draft the artifacts of safety analysis such as, losses, hazards, Unsafe Control Actions (UCAs), and safety constraints, inside rigorous processes such as Systems-Theoretic Process Analysis (STPA). Yet a blind spot runs through this fast-growing literature: every system gets analysed except the LLM-assisted tool doing the analysing, which is itself a safety-relevant system that can...
-
55
An exact information theory of generalization phase transitions in Bayesian diffusion models
Henry Hunt, Mason Kamb, Surya Ganguli
cs.LG · cond-mat.dis-nn
How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery. To address this, we introduce analytically tractable Bayesian information restricted diffusion (BIRD) models, in which each pixel observes restricted information about noisy data. A BIRD model time-reverses diffusion by inferring which past...
-
56
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
Ashwin Gerard Colaco, Nada Lahjouji
cs.LG
Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions. Because none of this memory is free, four largely separate research communities have each learned to compact it. They evict or quantize the KV cache, prune or distill prompts,...
-
57
Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment
Hyeju Shin, Chorwon Kim, Ryangsoo Kim, Hark Yoo, Jaein Kim
cs.LG
The emergence of vision language models with fewer than 3 billion parameters has accelerated the implementation of on-device multimodal intelligence. However, a detailed understanding of component-wise quantization remains a bottleneck for optimal deployment. This paper presents a systematic evaluation framework for empirically validating five hypotheses across six quantization configurations on the Jetson Orin NX and AGX. By separating the...
-
58
PGD-NO: A Neural Operator with Precomputed Geometry Decomposition for 3D Million-scale Physics Simulations
Weiheng Zhong, Jing Bi, Victor Oancea, Hadi Meidani
cs.LG
While neural PDE solvers have demonstrated significant potential for accelerating engineering simulations, existing architectures remain constrained by high memory consumption and the single node bottleneck, where the maximum processable mesh resolution is strictly limited by the VRAM of a single compute unit. To address these challenges, we propose PGD-NO, a neural operator with Precomputed Geometry Decomposition, that relocates the...
-
59
Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems
Shuo Huai, Di Liu, Hao Kong, Xiangzhong Luo, Weichen Liu, Ravi Subramaniam, Christian Makaya, Qian Lin
cs.LG · cs.DC
Federated Learning (FL) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. However, when deploying FL in real-time edge systems, the heterogeneity of devices among systems has a severe impact on the performance of the inferred model. Existing optimizations on FL focus on improving the training efficiency but fail to speed up inference,...
-
60
Provably Optimal Learning Algorithms for Assistance Games
Nivasini Ananthakrishnan, Mark Bedaywi, Michael I. Jordan, Stuart Russell, Nika Haghtalab
cs.LG · cs.AI · cs.GT
This paper studies an online variant of the assistance games framework, where an informed agent and an uninformed agent repeatedly interact over $T$ timesteps to optimize a common reward function. While the informed agent (the human) observes a latent state of the world, the uninformed agent (the assistant) observes only the human's actions. We provide the first provably efficient learning algorithms for repeated assistance games. We...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.