cs.LG · 2026-11-05 · No. 164
Machine Learning, 2026-11-05.
64 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
64 entries-
01
Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement
Michal Korniak, Marco Bagatella, Ralf Römer, Michal Nauman, Yarden As, Pranav Vignesh, Manan Agarwal, Leander...
cs.LG · cs.RO
The introduction of generalist robot policies has enabled a single, large model to learn to perform a variety of tasks from a vast pre-training corpus. While these models often exhibit powerful zero-shot generalization capabilities, they typically require an adaptation phase to achieve sufficient performance in deployment. Iterated self-improvement via reinforcement learning (RL) has demonstrated promise in enabling this adaptation, yet such...
-
02
Adaptive Multi Mode: Budget-Aware Routing of Optimizers By Online Landscape Probes
Benjamin Jacob Bodner
cs.LG · cs.NE · math.OC
The best classical optimizer for a continuous black-box problem depends on its budget and landscape. Existing routers decide from the dimension and budget, past improvement or features fitted to one benchmark, and few test an optimizer's implicit assumptions online. AMM (Adaptive Multi Mode) routes a known budget among quasi-Newton, trust-region, coordinate, multistart and evolution-strategy optimization engines with online probes of...
-
03
Navigating Disagreement Among Criteria for Evaluating Explanation Faithfulness
Grant Shanklin, Jiří Němeček, Asia Biega
cs.LG · cs.CY
Faithfulness requires that algorithmic explanations accurately reflect the model's behavior. Yet existing operationalizations of faithfulness can disagree about whether the same explanation is faithful, leaving developers and auditors to choose among conflicting evaluations. In this paper, we investigate disagreement among evaluation criteria and offer a practical path forward for evaluating explanation faithfulness. We first identify how...
-
04
Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token
Tommy He, Thomas Jiralerspong
cs.LG · cs.AI
Under stochastic decoding, a single context can elicit many different answers from a language model. Characterizing this variation typically requires many expensive autoregressive rollouts, each revealing only one realization. We ask whether the activations produced while reading the context can directly forecast the model's rollout activations. We train context--answer metamodels that map a context activation sequence to point or...
-
05
Systolic Linear Attention: Co-Designing Tile-Grouped Gated Delta Attention for TPUs
Gagik Amirkhanyan, Nuojin Cheng
cs.LG
Gated-delta linear attention layers such as Gated DeltaNet (GDN), Kimi Delta Attention (KDA), and GDN-2 are tuned for GPUs, where small tensor-core tiles and fast vector registers make per-channel decay rescaling and sequential in-block solves cheap. On Google TPUs, which concentrate compute in wide $256 \times 256$ systolic matrix units backed by a slower vector unit, porting these layers directly leaves half of each matrix tile empty and...
-
06
Message-passing graph persistence
Jorge Luiz Franco, Arthur Queiroz Moura, Moacir Ponti, Amauri Souza
cs.LG · cs.AI · stat.ML
Message-passing graph neural networks (GNNs) are limited in expressive power by the one-dimensional Weisfeiler-Leman test. Persistent homology (PH) provides topological descriptors that can complement GNN representations, but existing approaches typically compute persistence separately from the representation learning process. In this paper, we introduce Message-Passing Graph Persistence (MGP), a family of topological descriptors that...
-
07
Transforming Integer Grids to Spatial Intuition: Perception, Not Planning, Governs ARC-AGI-3
Harsidak Singh Banwait
cs.LG · cs.AI
Sample-efficient fluid intelligence requires agents that rapidly form working models of unfamiliar interactive environments. ARC-AGI-3 tests this across uninstructed visual games scored by Relative Human Action Efficiency, which penalizes exploratory waste quadratically. When frontier models read raw integer grids, serialization destroys spatial topology, and they spend hundreds of actions rediscovering basic boundaries and symmetries. We...
-
08
FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning
Quan Minh Nguyen, Hoang M. Ngo, Bhakti Chowkwale, Yasaman Keshtkarjahromi, My T. Thai
cs.LG · cs.AI
One-shot and few-round federated learning (FL) reduce communication burden by constructing a global model within one or a few communication rounds, but often achieve lower performance than conventional multi-round FL. Without frequent synchronization, client models may drift apart, causing neurons that learn similar features to occupy different positions across clients. At the same time, local data heterogeneity can cause corresponding...
-
09
Continual Classification Beyond the Kernel Regime: Harnessing the Sparsity Bias of L2 Regularization in Diagonal Linear Networks
Gilad Karpel, Itay Evron, Ron Meir, Daniel Soudry
cs.LG
We study logistic regression for continual learning with linear predictors in a high-dimensional statistical setting. Existing theoretical work has largely focused on continual linear regression with variants of L2 regularization, motivated by their analytical simplicity and connection to the kernel regime of neural networks. We first derive the optimal L2 regularization strength for continual linear classification and characterize its...
-
10
Template Gap Reconstruction for Shell Output Simulation with Small Language Models
Jarrod Ragsdale, Rajendra Boppana
cs.LG · cs.CL
Small language models offer a compact basis for shell simulation without executing submitted commands, but full-output decoding requires them to predict recurring utility structure alongside content that varies across executions. We introduce template gap reconstruction (TGR), which supplies reusable output literals interspersed with sentinels to be interleaved with autoregressively generated gaps. A template selector chooses which template...
-
11
Symmetry Breaking at the Edge of Stability via Central Flow Analysis
Naima Elosegui Borras, Georgios Arvanitidis
cs.LG
Continuous symmetries in neural networks lead to conserved quantities that are invariant under gradient flow, such as layer balancedness in linear and ReLU networks. Finite-step gradient descent need not preserve these laws, particularly at the edge of stability (EOS), where the iterates oscillate around a smoother trajectory, which can be described by the central flow dynamics (Cohen et al., 2025). We study how gradient flow conservation...
-
12
Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching
Giuliano Galadini, Aurelio Uncini, Danilo Comminiello
cs.LG · physics.comp-ph
Deep generative models, particularly Flow Matching frameworks, have emerged as powerful tools for synthesizing complex physical systems. However, standard architectures remain purely statistically driven and agnostic to the underlying governing equations, often violating fundamental physical constraints during inference. Existing zero-shot approaches designed to enforce these constraints typically rely on rigid algebraic projections. While...
-
13
Where It Breaks: Diagnosing Perception, Memory, and Decision Failures of a Vision-Language Agent in Pac-Man
Xinglu Wang, Edward Wang, Yong Zhang, Zhenan Fan
cs.LG
Training an agent to play Pac-Man with only up, down, left and right actions raises a basic question: when performance is poor, what should be improved? Difficulty can arise from reading the screen or from choosing actions over a long sequence. We examine these problems in a Qwen3.5-9B-based agent through separate perception checks and primitive-policy reinforcement-learning studies. In the policy study, which uses textual boards to remove...
-
14
PINR-ESI: Physics-Informed Self-Supervised Implicit Neural Representation Framework for EEG Extended-Source Imaging
Zhiyong Zhou, Sheng Liao, Youshen Xiao, Xiaolin Li, Yakang Dai
cs.LG · q-bio.NC
EEG extended-source imaging aims to localize active cortical regions and characterize their spatial extent, yet supervised inverse networks typically depend on synthetic EEG-source pairs and may be sensitive to synthetic-to-real mismatch. We propose a physics-informed self-supervised implicit neural representation (INR) framework for spatial source reconstruction without paired source labels or simulation-based supervised pretraining. The...
-
15
Don't Replace, Complement: A Detector-Agnostic Subspace Signal for Near-OOD Detection
Wonseok Shin, Songkuk Kim
cs.LG · cs.AI
Post-hoc out-of-distribution (OOD) detection is mature on far-OOD yet remains weak on near-OOD. These two settings differ in their use of class-characteristic feature directions: far-OOD inputs largely fail to activate those of their predicted class, whereas near-OOD inputs activate them much as in-distribution samples do. Because the axis separating far-OOD leaves near-OOD almost indistinguishable from ID, a score optimized for one setting...
-
16
SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents
Guoqin Xiong, Shengtao Wen, Xiang Chen, Xinyi Zeng, Zhaoxin Fan, Wei Ye, Xiaofeng Cao, Sheng-Jun Huang
cs.LG
Tool-using large language model (LLM) agents translate model outputs into consequential actions, turning indirect prompt injection into an execution-security problem. Existing defenses constrain tool calls, trajectories, or information flows, but often leave action semantics, state dependencies, and evidence relations implicit, limiting generalization across heterogeneous tools and complicating safe updates. We present \ours{}, a dynamic...
-
17
Do unlearning algorithms learn the right features?
Polina Dolgova, Amartya Sanyal, Sebastian U. Stich
cs.LG
Machine unlearning is commonly evaluated with standard post-deletion metrics that compare an unlearned model to one retrained on the remaining data. Such snapshot evaluations can conceal consequential differences in the features the two models encode. We prove that if an unlearned and a retrained model agree on their outputs but encode different features, a single gradient step on their prediction heads can break this agreement. We further...
-
18
Self-Directed Apple Tasting
Tanmay Devale, Reed Phillips, Arvind Ramaswami
cs.LG
We study the classical apple-tasting setting, a partial feedback model in which the learner observes the true label only when it predicts $1$. A combinatorial characterization for the rates of this problem in the online adversarial setting has been studied by Raman et al. (2024). We study the self-directed setting, in which the learner can adaptively choose the order of the points it predicts on. In the realizable setting, we establish a...
-
19
Fingerprinting the Dispatchers behind Distributed Model Extraction
Snigdha Chandan Khilar
cs.LG
API distillation campaigns try to hide model-stealing traffic by splitting requests across thousands of load-balanced accounts, which standard content classifiers often miss. However, request timestamps, specifically arrival time and stream completion time, reveal the underlying dispatching strategy, such as round-robin counters or key-shuffling pools. Using a 20 percent seed set, this timing analysis can forensically rank the remaining...
-
20
Dimension-Free Private Mean Estimation is Impossible Without the Covariance
Renaud Gaucher, Ephraim Linder, Adam Smith, Jonathan Ullman, Lydia Zakynthinou
cs.LG · cs.DS
We study the limits of differentially private Gaussian mean estimation when the covariance matrix is unknown. Prior work shows that when the covariance $Σ$ is known, the optimal sample complexity can depend only on its spectrum, rather than on the ambient dimension $d$. We establish new lower bounds for Gaussian mean estimation with Euclidean error which show that private estimators cannot achieve similar guarantees when the covariance is...
-
21
From Reconstruction to Imputation: Test-Time Optimization for Missing Time-Series Channels
Björn Ludwig, Alexander Windmann, René Heesch, Oliver Niggemann
cs.LG · cs.AI
Complete sensor-channel failures create a difficult form of time-series missingness: local interpolation is unavailable, and deploying a separately trained imputer for every failure pattern may be impractical. We ask whether a sequence reconstructor trained without artificial mask augmentation and then frozen can be converted into an imputer at inference time. Our method treats the missing entries of each test window as optimization...
-
22
Alternatives to Shallow Autoencoders for Collaborative Filtering
Mario Mallea, Angela Nebot, Francisco Mugica
cs.LG · cs.IR
Collaborative filtering (CF) is a cornerstone of recommender systems and plays a relevant role in many modern applications. CF uses user-item interaction data to discover future preferences. Although deep learning models have shown promise in CF, Embarrassingly Shallow Autoencoders for Sparse Data (EASE) has gained attention for its outstanding ranking accuracy provided by its closed-form solution. EASE relies primarily on relationships among...
-
23
Verifier-Guided Self-Consistency: Test-Time Reasoning with Imperfect Generators and Verifiers
Ekaterina Fadeeva, Xueyan Li, Mrinmaya Sachan, Maxim Panov
cs.LG
Large language models can solve many multi-step reasoning problems, but their reasoning remains brittle: plausible intermediate steps often lead to incorrect answers. Improving reasoning at test time requires balancing two imperfect signals: the generator, which provides diversity, and the verifier, which guides correctness. Existing approaches largely favor one side of this tradeoff. Verifier-weighted voting relies on trajectories sampled...
-
24
The Behavioral Rate of Fine-Tuning: Compression as a Measure of Useful Information
Joey David, Paul Caillon, Alexandre Allauzen
cs.LG
Low-Rank Adaptation (LoRA) adapts a frozen language model through a compact learned update, making it a natural setting for asking how much information fine-tuning needs to write. Yet adapter rank, parameter count, or numerical reconstruction error do not directly tell us how many bits are required to preserve the acquired behavior. We therefore define an operational behavioral rate $R^\star$ as the smallest serialized size of a compressed...
-
25
A trust layer for fast pedestal-stability surrogates: calibrated error bars, out-of-distribution alarms and few-shot recalibration
Amin Vakhshouri
cs.LG · physics.plasm-ph
Machine-learning surrogates of linear peeling-ballooning stability now run in milliseconds, but they are mostly deployed as point estimators: they do not say how wrong they may be, or when a query lies outside what they were trained on. For a fusion company designing a new device, every equilibrium of interest is outside the training data of existing surrogates, so this is the case that matters. We describe a model-agnostic trust layer for...
-
26
Thermodynamics-Informed Learning Captures Hierarchical Hydrogen-Bond Networks in Deep Eutectic Solvents
Yanpeng Ye, Chaoran Duan, Mian Xu, S. Mani Sarathy
cs.LG · physics.chem-ph · quant-ph
Deep eutectic solvents (DESs) offer a tunable platform for lignocellulose refining, but their solvation behavior depends on multicomponent hydrogen-bond networks rather than individual constituent properties. We develop TiNN, a thermodynamics-informed neural network that hierarchically represents HBA-HBD association and solute accommodation through a learned free-energy pathway. Trained on 938 records, TiNN achieves a test-set $R^2$ of 0.917...
-
27
From Fixed Defaults to Calibrated Activation Policies for Long-Term Time-Series Forecasting
Shijie Xu, Boyan Tang, Jianghua Wu
cs.LG
Long-term time-series forecasting supports decisions in energy, transportation, and other applications where reliable predictions are needed beyond the observed data. Although forecasting research has advanced model architectures, fixed activation configurations provide limited guidance on how activation choices should vary across datasets and prediction horizons. This study aims to establish when task-specific activation choices improve...
-
28
EvoOPD: Evolving Privileged Information Strategies for Black-Box On-Policy Distillation
Ximo Zhu, Ruiqi Liu, Yi Han, Zhengan Wu, Gengsheng Li, ZiAn Wang, Zhu Yuantian, Jin Jiang, Wenhao Wang
cs.LG
Proprietary language models exhibit strong reasoning and coding capabilities, but their output distributions are inaccessible, making fine-grained distillation methods that rely on teacher logits difficult to apply directly to black-box models. We observe that rich textual feedback from a black-box teacher can be treated as privileged information (PI) and converted, through a PI-conditioned privileged teacher, into dense supervision signals...
-
29
IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning
Deeraj SK, Sadhana Devarajan, Tanmoy Hazra, Anupam Shukla
cs.LG · cs.AI
Machine unlearning removes the influence of specific training examples to comply with privacy regulations. Full retraining gives strong guarantees but is computationally prohibitive at scale; approximate methods are efficient but lack formal guarantees. SISA (Sharded, Isolated, Sliced, and Aggregated training) achieves certified deletion through data sharding and independent retraining, but random partitioning scatters forget requests across...
-
30
An Interaction-Aware Decision Framework for FDIC-Assisted Distressed Bank Acquisitions: Empirical Evidence from the FDIC Failed-Bank Panel and the SVB-First Citizens Case
Yousef Nejatbakhsh, Malihe Aliasgari, Parsa Safaee, Sina Shokoohyar
cs.LG · stat.AP
Acquirers of failed banks weigh acquisition value, regulatory protection, risk, buyer strength, and execution difficulty jointly, because each signal's meaning depends on the others: high non-performing loans matter less when government loss sharing absorbs the losses. The proposed Spider Network Filtering Framework encodes such dependencies as four interpretable interaction rules among five dimensions, yielding graph-inspired features for a...
-
31
Nowcasting Future Performance for Population Pruning in Survival-of-the-Fittest Training
Rico Städeli, Léo Meynent, Boris Knyazev, Damian Borth
cs.LG
Training high-performing neural networks often involves evaluating populations of candidate models with varying hyperparameters, architectures, or random seeds. Training every candidate to completion is computationally expensive, yet stopping seemingly weaker runs early risks discarding models that would ultimately perform better, as learning curves can cross. To address this challenge, we investigate whether intermediate training checkpoints...
-
32
Model Merging Does Not Require Uniform LoRA Ranks
Zirong Xie, Zainab Afolabi, Nikita Kozodoi, Jack Butler
cs.LG · cs.AI
Model merging combines separately fine-tuned experts into a single model without retraining. Standard practice trains every expert at the same LoRA rank, which couples the rank choice across experts even though each domain has its own best rank. We show this coupling is a property of the merge method, not of merging. We train 36 experts on three domains (mathematics, instruction following, multilingual) at four ranks and three model scales,...
-
33
What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?
Kejian Zhu, Zhuoran Jin, Shangqing Tu, Tianyi Men, Yupu Hao, Jiachun Li, Kang Liu, Jun Zhao
cs.LG · cs.CL
While multi-turn agentic reinforcement learning (RL) excels on long-horizon tasks, its performance gains remain highly sensitive to interaction constraints. Evaluating across sampling breadth $K$ and interaction depth $T$ via $Pass@(K,T)$, we show that trajectory-level RL advantages depend on sufficient turn budgets, diminishing significantly when budgets tighten. Besides, agentic RL does not uniformly elevate single-step decision quality;...
-
34
The Alignment Tax Is Graded: Task-Selective Capability Loss Under Length-Normalized DPO with SFT Retention
Ye Yuan
cs.LG
Setting. This is an empirical characterization study; we propose no new method and run no comparisons against alternative objectives. We fine-tune Qwen3.5-4B with sparse LoRA and length-normalized DPO plus an SFT retention term (the RPO objective) on structured financial-filing tasks, and track downstream capability as the implicit reward margin grows to $\sim 7$ $β$-scaled units (nf4 training; $\sim 3$ under fp16 measurement on the...
-
35
Graph Foundation Models Can Become Effective Multivariate Time Series Anomaly Detectors
Zhuangyan Hu, Zhuoxuan Liang, Wei Li, Xiaohua Jia, Moustafa Youssef, Sumi Helal
cs.LG
Multivariate time series anomaly detection (MTSAD) relies on modeling both temporal dynamics and inter-sensor dependencies to identify complex system faults. Although graph-based detectors explicitly model sensor topologies, they train task-specific networks from scratch on limited target-domain data, remaining vulnerable to spurious correlations and unable to reuse transferable priors. While pretrained Graph Foundation Models (GFMs) offer...
-
36
Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
Nuo-Jing Liang, Xiao-Tong Yuan, Pan Zhou
cs.LG · stat.ML
Chain-of-Thought (CoT) reasoning substantially improves Large Language Models (LLMs), yet its out-of-distribution (OOD) generalization mechanism remains theoretically underexplored. We study CoT as compositional OOD generalization: the target task lacks complete reasoning trajectories or direct input-output pairs, while training provides only in-distribution (ID) atomic step data. We show that CoT generalizes by repeatedly applying a shared...
-
37
Partially Interpretable Decision Trees
Ludovic Schwartz, Federico Berton, Tim van Erven
cs.LG
Partially interpretable models extend simple interpretable models with the option to defer complicated inputs to an accurate but uninterpretable black-box model. By deferring more inputs, the model gets more accurate; by deferring fewer, it gets more interpretable. Existing procedures to train such partially interpretable models build on linear models or decision rules. We propose three algorithms for decision trees: a partially interpretable...
-
38
Zero-Shot Coordination among LLM Agents
Adrian Hayler, Shashank Reddy Chirra, Andrei Lupu, Johannes Forkel, Bidipta Sarkar, Siheng Feng, Jakob Foerster
cs.LG · cs.AI
We study zero-shot coordination (ZSC), where independently developed agents must coordinate at test time. While ZSC has been well studied in the RL literature, far less is known about the performance of LLM agents despite their increasing deployment in such settings. Existing work on LLM coordination often relies on specialised scaffolding that independently developed agents are unlikely to share in practice. Moreover, evaluations on complex...
-
39
KolTa: A Physics-Informed Active Learning Framework for Formulation Discovery with Limited Data
Boyong Tang, Tao Wang, Lei Yang
cs.LG
Finding high-performing formulations is difficult when few have been measured and experimental budgets are limited. We propose KolTa, an active learning framework that selects batches to discover the top 5% of formulations at a target temperature under a fixed query budget. KolTa combines a three-stage predictor of component contributions, role-conditioned interactions, and anchored temperature response with task-specific soft physics...
-
40
From hydrological laws to catchment models: A process-based model matches deep-learning accuracy on three continents
Xilin Xia
cs.LG · cs.AI · math.DS · physics.geo-ph
Dooge asked whether hydrology has laws at the catchment scale. We ask whether a low-dimensional system built under physical laws can match the accuracy of neural networks that outperform process-based models on the same inputs. Three laws constrain a lumped catchment model. Conservation makes it a flux-connected storage network, dissipation fixes the sign of every flux and aggregation determines how the unresolved composition enters the...
-
41
Give Up to Get More: Priors, Not Policies, Govern Test-Time Compute Allocation
Jinhyung Bae
cs.LG
When many inputs share a budget of repeated attempts by a large language model (LLM), a common rule gives harder inputs more. On public math, code and formal-proof samples, the best published difficulty-proportional rule captures half or more of the oracle gain on benchmarks the model mostly solves, but at most 13% on hard workloads, even given true pass rates. Because the value of one more attempt peaks at intermediate difficulty, the...
-
42
EEGDash Corpus: A Training-Ready Public Corpus for EEG Foundation Models
Kuber Shahi, Bruno Aristimunha, Arnaud Delorme
cs.LG
Foundation models for electroencephalography (EEG) are pretrained on tens of thousands of hours of recordings, and their accuracy grows with that amount. Such data is hard to assemble. The largest sources are clinical archives that cannot be redistributed, and the public sources are spread over several archives, file formats, and licences. We release eegdash-corpus-v0, a training-ready corpus of 77 public EEG datasets, as the gated Hugging...
-
43
Flexible Intensities Matter: A Comprehensive Re-evaluation of Hawkes Processes and Neural Temporal Point Processes
Hendrik Mehrtens, Florian Buettner, Oliver Stegle
cs.LG · stat.ML
Temporal point processes (TPPs) are the canonical framework for event sequence data, with applications spanning seismology, social media, and electronic health records. Recently, neural TPPs have been reported to substantially outperform classical TPPs, such as Hawkes processes, but these comparisons pitted flexible neural models against Hawkes processes in their most restricted form, and did not consider large-scale medical data. Here, we...
-
44
Learning to Tune with Biased Gradients: Iterative Feedback Tuning of Model-Free Control on Throttle Valves
Félix Martinez-Jiménez, Sander Miller-Murphy, Tobie Ondoa-Essomba, Emmanuel Witrant
cs.LG · cs.AI
Iterative feedback tuning (IFT) learns the parameters of a fixed-structure controller by stochastic gradient descent. At each iteration, two closed-loop experiments are run on the plant: the first one measures the tracking error, and the second one, driven by this error, provides the sensitivities from which the gradient of the cost is estimated. This estimate is unbiased for linear plants only. We study the biased case on automotive...
-
45
Conformal Prediction for Distribution-to-Distribution Regression
Trung-Khang Tran, Tuan A. Hoang, Viet-Hoang Tran, Tan M. Nguyen
cs.LG · cs.AI
Conformal Prediction (CP) provides a model-agnostic framework for constructing finite-sample prediction sets with coverage guarantees and has become a tool for reliable decision-making in high-risk settings. Recent advances have extended Split Conformal Prediction to increasingly complex learning problems, including multilabel, high-dimensional, and functional outputs. In this work, we study CP for Distribution-to-Distribution Regression, a...
-
46
When Does Risk-Controlled Throughput Forecasting Actually Control Risk? A Reproduction Study on LEO Satellite Link
Mayan Sharma, Kriti Saini, Devansh Behl, Suganya R, S. Vijayaragavan
cs.LG · cs.AI · cs.NI
Risk-budgeted throughput forecasting converts a point forecast of LEO satellite capacity into a conservative bound whose overestimation rate is held at a user-specified budget, so that admission control can act on it safely. We reproduce the state of the art, BG-CFQS, on the three Starlink traces its authors used and on an independent fourth dataset, and report four findings. First, its risk guarantee is reproducible but conditional on the...
-
47
The Split Protocol Decides the Result: Re-Evaluating Encrypted Traffic Classification
Mayan Sharma, Kriti Saini, Devansh Behl
cs.LG · cs.AI
Encrypted traffic classifiers are routinely reported at 95-99% accuracy. We show that on one of two public corpora, the same model and code score macro-F1 0.992 under the evaluation protocol standard in the literature and 0.567 under a protocol that keeps flows from one packet capture on one side of the split. Nothing changes but the partition (gap 0.426 over eight seeds, p = 0.008 after Holm-Bonferroni correction). The inflation is not a...
-
48
Consistency Learning and Distillation for One-Step MIMO-OFDM Channel Estimation
Fredrik Nguyen, Qiwen Wang
cs.LG · eess.SP
Iterative neural channel estimators can improve recovery under pilot contamination, but repeated network evaluations increase inference cost. This paper develops observation-anchored consistency and Consistency Mid-Training (CMT) estimators for one-step channel estimation in multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems. Both estimators refine pilot-derived least-squares channel estimates in the...
-
49
Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
Yun Young Choi, Asung Kil, Sun Woo Park, Minho Lee, Seokhwan Kim
cs.LG · cs.AI
Several widely used families of Graph Neural Networks carry a positive-definite geometric prior. Graph convolution read as heat diffusion needs a positive semi-definite operator, hyperbolic models place features on positive-definite Riemannian manifolds, and dot-product and GAT-style attention scores use positive-definite inner products. On heterophilic graphs, where edges often signify dissimilarity or structural repulsion, that prior is a...
-
50
Learning Noise Optimization for Reward Alignment in Few-Step Generative Models
Hongeun Kim, Jeongsol Kim, Jong Chul Ye
cs.LG
Reward alignment for diffusion- and flow-based generative models is often formulated over stochastic trajectories, making it less suitable for few-step deterministic generators. Initial noise optimization provides a trajectory-free alternative, but existing gradient-free methods require costly per-sample search at inference. We introduce LeNO (Learning Noise Optimization), which amortizes reward-guided initial noise optimization into a...
-
51
Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
Sumeet Ramesh Motwani, Tejas Krishnan, Alistair Letcher, Charles London, Suhaas Bhat, Huitian Jiao, Philip Torr,...
cs.LG · cs.AI
Reinforcement learning with verifiable rewards (RLVR) has led to significant gains in math and code generation. Extending these gains to open-ended domains remains challenging: ground-truth verification is unavailable, human annotation is expensive, and learned reward models are prone to reward hacking. The generation-verification gap, where judging good outputs is easier than producing them, offers a potential path to improvement. However,...
-
52
Separation Is a Riesz Energy: How Many Environments Does ICA Need?
Yuda Bi, Yubo Guo, Jiaxiao Cai, Xiaonai Li, Zhuolin Li, Vince D. Calhoun
cs.LG · cs.IT · stat.ML
Can independent components be recovered when all of them are Gaussian? Yes, if their variances change across environments; but how many environments, and how many samples as the number of components $d$ grows? We answer both for the joint diagonalization of $K$ covariances. Each component has a signature, its variances across the environments. Separating component $j$ costs the Riesz 2-energy $E_j$ of this signature, a sum, over the other...
-
53
Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data
Zekai Wang, Yuxuan Li, Zhangyue Shi
cs.LG
Reliability management of industrial fleets depends on early fault warnings, yet lifecycle data across similar assets are highly imbalanced. A few assets accumulate run-to-failure histories, while newly installed or rarely failing assets provide only normal-condition data. This paper asks how diagnostic knowledge can be transferred from a data-rich source asset to a data-scarce target asset when no fault data have been observed on the target....
-
54
GPUMAP: GPU-Accelerated Progressive Uniform Manifold Approximation and Projection
Myeongwon Jung, Jaemin Jo
cs.LG · cs.GR · cs.HC
Dimensionality reduction (DR) techniques are fundamental to the analysis of high-dimensional data, yet their substantial computational cost limits their use in interactive settings. To address this limitation, we present GPU-accelerated Progressive Uniform Manifold Approximation and Projection (GPUMAP), an efficient progressive DR algorithm designed for interactive use. We identify three atomic operations within UMAP and restructure them into...
-
55
FaCoDiff: Factor-Correlated Diffusion for Multivariate Probabilistic Forecasting
Jiaxuan Li, Yao Liu, Yuewei Xue, Shijie Dong, Zixiang Jin, Xiaoyu Guo, Qiao Liu
cs.LG
Multivariate probabilistic forecasting requires modeling cross-variable dependence alongside marginal uncertainty. The challenge is to learn this dependence while controlling marginal noise scales and avoiding dense covariance costs. We propose Factor-Correlated Diffusion (FaCoDiff), which couples a compact conditional statistical estimator with structured denoising. History-conditioned factor loadings use distinct coefficients for...
-
56
Selective Prediction Intervals: Jointly Learning to Predict, Bound, and Abstain
Lidor Rubi, Gilad Katz
cs.LG
Many high-stakes regression decisions ask three things of a model at once: a point estimate to act on, an interval that bounds the risk of acting, and the option to abstain when neither can be trusted. Deep learning provides these in isolation: prediction-interval methods return an interval, and at best a value estimate inside it, for every input, while selective-prediction methods learn when to abstain, but only for point predictions and...
-
57
Neural Stochastic Forecasting for Lateral Molecular Diffusion Simulations
Jacob Ede Levine, Mario Hidalgo-Soria, Chen Yun Wen, Yun Lyna Luo, Sai Chandra Kosaraju
cs.LG
Predicting the long-time diffusion of membrane proteins is challenging because molecular dynamics (MD) simulations are computationally expensive, while experimental single-particle tracking is often limited by finite observation times. Here, we introduce a neural stochastic (NS) model for forecasting the collective diffusion of membrane proteins from coarse-grained MD trajectories. The model combines a transformer-based representation of...
-
58
Short-Term Forecasting of Heterogeneous Wind Power Fleets: Global Temporal Fusion Transformer Leveraging Static Covariates
Viktor Walter, Andreas Wagner
cs.LG
Accurate short-term wind power forecasting is critical for grid stability and electricity trading. While transformer-based deep learning is state of the art, industry practice relies mostly on local models trained for individual assets. This study investigates whether a global temporal fusion transformer (TFT), trained jointly on a heterogeneous portfolio of wind farms across Germany, outperforms site-specific local models in 48-hour-ahead...
-
59
Learning When to Think Aloud in Latent Reasoning
Zhehao Zhou, Tongrui Su, Shengyu Zhu, Da Li, Zeyu Liu, Jun Zhu, Xueqi Cheng
cs.LG
Latent Chain-of-Thought (CoT) reasoning improves efficiency by shifting intermediate computation into continuous hidden states. However, fully latent methods often struggle on precision-critical tasks such as mathematical reasoning, while existing hybrid approaches retain substantial token-generation overhead. We introduce VITAL, an importance-guided hybrid reasoning framework that selectively verbalizes informative tokens as reasoning...
-
60
Shallow Encoding Emits Deep Memories
Mingyuan Ma, Yangmin Li, Harris Nover, Zheyu Fu, Po-Han Huang, Alex Settle, Ashwin Nanjappa
cs.LG · cs.DC
Hybrid language models interleave a few softmax-attention layers with many linear-attention or state-space layers, so every layer keeps a memory of earlier tokens: a key-value cache or a fixed-size recurrent state. Serving them spends more compute and high-bandwidth memory on these memories than the output requires. The prefill runs every layer for every prompt token, and every decode step loads and stores whole recurrent states, which on...
-
61
Catastrophic Overfitting is Weight Drift the Training Loss Cannot See
Chao Pan
cs.LG · cs.CR
Fast adversarial training (FAT) makes robust training affordable by replacing the multi-step attack with a single-step one, but it suffers from catastrophic overfitting (CO): partway through training, robustness to multi-step attacks collapses to near zero while the single-step attack used for training keeps being repelled. We show that CO is a quiet escape of the weights. Across the event the network's clean behavior quietly improves, and...
-
62
PRISM-AMC: Replay-Free Continual Learning for Automatic Modulation Classification
Usman Akram, Matthew Graham, Haris Vikalo
cs.LG · eess.SP
Automatic modulation classification (AMC) is a key component of cognitive wireless systems, enabling spectrum awareness and adaptive communication. Most deep learning approaches to AMC assume a fixed set of modulation classes and access to previously observed training data. In practice, modulation classes and channel conditions may evolve over time, while storage or data-retention constraints may preclude replay of raw baseband I/Q samples....
-
63
Learning From Static Context in Federated Time Series Forecasting
Viktor Walter, Andreas Wagner, Fabian Stricker
cs.LG
Time series forecasting is shifting from locally trained, per-series models to global models trained across many heterogeneous series, which requires learning what sets the series apart. When the raw data cannot be centralized, such a global model is trained with federated learning (FL), one client per data owner. State-of-the-art forecasters such as the Temporal Fusion Transformer (TFT) tell series apart through a static input that describes...
-
64
Alleviating Limited Effectiveness and Multi-Class Collapse in Deep Graph-level Clustering
Xiaoyang Lin, Renchi Yang, Yuqi Chen, Xin Huang
cs.LG
Given a collection of $N$ graphs, graph-level clustering (GLC) seeks to partition the $N$ graphs into semantically meaningful groups, which serves as a fundamental task in analyzing graph-structured data. While Graph Isomorphism Networks (GINs) have become the de facto encoders for GLC, they still fail to distinguish graphs due to their neglect of global topology. On top of that, existing deep clustering frameworks suffer from severe...
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.