cs.LG · 2026-10-16 · No. 145
Machine Learning, 2026-10-16.
72 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
72 entries-
01
PathFM: Fast Generative Forecasting of Multivariate Trajectories
Jiachen Yao, Xiyuan Zhang, Annan Yu, Boran Han, Abdul Fatir Ansari, Shuai Zhang, Michael Bohlke-Schneider, Bernie Wang
cs.LG
Time series foundation models are becoming increasingly popular for general-purpose forecasting. However, most leading models predict marginal quantiles, leaving the dependence structure of future trajectories unspecified. This distinction matters for trajectory-dependent quantities such as cumulative demand, peak load, and event timing, yet point and marginal scores do not reveal it. To model this dependence, we introduce PathFM, a...
-
02
Rethinking Routing Exploration in Modern Mixture-of-Experts
Bingcong Li, Hao Ma, Michael Muehlebach, Niao He, Yi Ma
cs.LG · cs.AI
Mixture-of-experts (MoE) models have become an important approach for scaling model parameters. Modern MoE architectures increasingly combine two design choices: fine-grained expert segmentation and shared experts. The former increases expressiveness by enabling more expert combinations at a fixed activation ratio, and the latter introduces experts that are active for every token. We identify an exploration dilemma between these designs:...
-
03
Lean Graph Search for Formal Theorem Proving
Yihan Xu, Jia-Chen Gu, Junyi Zhang, Di Wu, Haikang Deng, Po-Nien Kung, Kai-Wei Chang, Amit Sahai, Wei Wang, Nanyun Peng
cs.LG
Retrieving relevant lemmas is crucial for formal theorem proving, enabling provers to build machine-checkable proofs from established mathematical results. Recent retrieval systems match library declarations to a target theorem or its intermediate proof steps, but make limited use of multi-hop dependencies among declarations. These dependencies can reveal supporting lemmas that are not necessarily lexically similar to the target theorem but...
-
04
Robust Reinforcement Learning for Dynamic Treatment Regimes under Model and Measurement Uncertainty
Chengze Xie, Xuan Wang, Ying Ding, Hairong Wang, Yan Li
cs.LG
We develop a robust reinforcement learning (RL) framework for learning adaptive treatment policies that generalize across patients and remain reliable under errors in the measured biomarker and shifts in the disease dynamics. By modeling the patient as a hidden context, we address generalization and robustness in a unified manner through robust contextual Markov decision processes. Applying our framework to adaptive therapy for metastatic...
-
05
Twice Upon a Time: Complementary Representations for Time-Series Reasoning
Hedi Zisling, Liran Nochumsohn, Ilan Naiman, Mihir Parmar, Omri Azencot
cs.LG · cs.AI · cs.CL
Time Series Language Models (TSLMs) enable language-based understanding and reasoning over temporal data, yet a fundamental question remains: what information should their time-series representations preserve, and what variation should they factor out? Existing TSLMs typically expose the language model to a single representation, imposing a fixed inductive bias across downstream tasks. We instead introduce complementary representations as a...
-
06
Learning to Steer LLM Agents and Multi-Agent Systems
Leyang Shen, Yaxin Gong, Yang Zhang, Chenxiao Fan, Jiakai Wang, Dong Wang, Yang Liu, Fuli Feng, Chun Kai Ling, Tat-Seng Chua
cs.LG · cs.AI · cs.MA
Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. However, these systems are prone to deviating from the overall goal as execution unfolds, which wastes execution resources and leads to undesired outcomes, a failure termed goal drift. In this work, we propose a steering agent that supervises execution on the fly and steers the system...
-
07
Towards Continual Learning: Mitigating Forgetting With Subspace Tuning
Arnav Chavan, Kusha Sareen, Rishabh Tiwari, Abhranil Chandra, Johan Obando-Ceron, Kurt Keutzer, Scott Niekum,...
cs.LG · cs.AI
Large language models (LLMs) acquire new skills through fine-tuning, but it can destroy capabilities they already have: catastrophic forgetting remains a central obstacle to continual learning in LLMs. Recent works connect forgetting to how far, and along which directions, fine-tuning moves the weights. On-policy methods such as reinforcement learning and on-policy distillation avoid updating the principal singular directions of weight...
-
08
CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty
Yuan-Chen Chang, Niklas Herbster, Gauthier Gidel, Tommaso Tosato
cs.LG · cs.CL · cs.CY
Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still exhibit dishonest behaviour, such as outputting claims that contradict some knowledge or are not supported by what is accessible in context. We introduce Continuous Adversarial Training for Consistent Honesty (CATCH), inspired by a method originally developed to robustly refuse harmful queries....
-
09
Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems
Omar Adalat, Edwin Hamel-De le Court, Francesco Belardinelli
cs.LG · cs.LO · cs.MA
We study rational synthesis for stochastic multi-agent systems with unknown dynamics, where each agent is equipped with its own probabilistic temporal objective specified using Probabilistic Linear Temporal Logic on Finite Traces ($\mathsf{PLTL}_f}$). We impose solution concepts (e.g., Nash equilibrium, subgame-perfect equilibrium) as constraints on the joint strategy profile, using payoffs derived from each agent's probability of satisfying...
-
10
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
Anikait Singh, Teresa Zhang, Yoonho Lee, Roshen Sanjay Nair, Aviral Kumar, Chelsea Finn
cs.LG · cs.AI · cs.CL
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, cross-document reasoning at inference time, while precomputed structures like knowledge graphs often fall short because they rely on rigid heuristics. Instead, can we allow agents to perform anticipatory directed curation: learning to proactively reorganize...
-
11
Baselines and Score Centering in Policy Gradient Estimation
Shuo Han, Ziqing Hu
cs.LG
Reinforcement learning has become a widely used approach to post-training large language models. In a typical implementation, learning is off-policy: The policy generating the responses differs from the policy being trained because of training-inference mismatch or policy staleness in asynchronous training. This discrepancy is commonly addressed by importance sampling, whose ratio is usually regularized in practice through truncation,...
-
12
Topology-Inspired Fine-Tuning for Wind-Field Super-Resolution
Arjun Dadhwal, Brian Summa
cs.LG
Scientific super-resolution (SR) models are typically optimized with pointwise reconstruction losses, yet scientific interpretation often hinges on extrema, connected regions, and multiscale scalar structure. We characterize this tension with pretrained CNN and GAN wind-field SR models. Pointwise metrics, bottleneck persistence-diagram (PD) distance, and merge-tree (MT) distance favor the CNN, whereas order-2 Wasserstein PD distances favor...
-
13
BitSparse: Compact Activation Storage for ReLU Feed-Forward Networks
Max Zhu, Bohang Sun, Pietro Lio, Jialin Yu
cs.LG
Reducing memory use in large language model (LLM) training is an ongoing challenge. Activation checkpointing saves memory by recomputation, while lossy compression changes the stored activations. The reemergence of sparse $\relu$ and $\relu^2$ activations creates a third opportunity: losslessly compressing the activation cache itself. We present BitSparse, a GPU-resident lossless compression format for sparse activations. Compression and...
-
14
Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits
Spyros Dragazis, Yilei Chen, Aldo Pacchiano
cs.LG · stat.ML
We study how to evaluate $K$ target policies simultaneously in stochastic contextual bandits with linear reward structure. Given a known $d$-dimensional feature map and reward-free access to policy queries, we propose PRISMA (Policy evaluation through Regularized Information Sharing and Mixture Allocation), an algorithm that estimates every target policy's value to accuracy $\varepsilon$ with probability at least $1-δ$. The algorithm uses...
-
15
Query-Efficient Rejection Sampling for Parallel Masked Diffusion
Shiyuan Zhang, Xuheng Li, Qiwei Di, Quanquan Gu
cs.LG · math.PR · stat.ML
Masked diffusion models (MDMs) accelerate generation by unmasking multiple tokens in parallel, but sampling these tokens independently ignores their correlations and biases the output. Anari et al. (2026) corrected this bias with rejection sampling, decomposing the log acceptance probability into a sum of token-level terms, but the evaluation requires one score query per unmasked token. We propose the Single-Increment Rejection Sampler...
-
16
Training-Free On-Policy Distillation
Bangji Yang, Jiajun Fan, Zhaoyu Zhu, Hongbo Ma, Ge Liu
cs.LG · cs.AI · cs.CL
On-policy distillation consolidates specialist models into one student at the price of rollouts, teacher passes and gradient steps for every teacher. We show that the consolidation does not need training: with forward passes only, the capabilities of separately tuned specialists can be aggregated into one model that is, on average, more accurate than either specialist alone. When specialists share a base model, distillation has an exact...
-
17
OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
Bowen Yang, Kaiming Jin, Zichen Ding, Zhenyu Wu, Zehao Li, Zhoumianze Liu, Kanzhi Cheng, Fangzhi Xu, Yanan Sun,...
cs.LG · cs.AI · cs.CV
Real desktop automation is neither purely visual nor purely programmatic. Agents must understand user-facing interfaces while efficiently manipulating files, scripts, and system state. However, native GUI/code coordination cannot be obtained by prompt-level tool composition. In our preliminary experiments, naively adding a code tool degrades a GUI agent, revealing that GUI/code routing must be internalized through training on high-quality...
-
18
Generalization Guarantees of Randomized Block Coordinate Descent for Nonconvex Learning
Ruixi Hu, Liang Wu
cs.LG
Randomized block coordinate descent (RBCD) is a popular optimization algorithm for many large-scale machine learning problems. The existing theoretical analysis of RBCD mainly focuses on its convergence behavior from an optimization perspective, while its generalization behavior remains less understood for nonconvex problems. In this paper, we establish high-probability generalization guarantees for RBCD with nonconvex objectives. In the...
-
19
LCT: Losslessly Compressed Tensors with GPU friendly execution for Training
Max Zhu, Bohang Sun, Pietro Lio, Jialin Yu
cs.LG
Lossless tensor compression could reduce memory usage during training, but training requires tensors to be repeatedly re-encoded. We introduce Losslessly Compressed Tensors (LCT), a GPU execution framework designed for this repeated encode-decode regime. LCT exploits the natural redundancy in floating point data to reduce storage for weights, activations and optimizer states. Highly optimized GPU kernels implement Huffman coding with...
-
20
The importance of tensor handling and implementation of physics-informed DeepONets
Nahum Banks, Gustavo A. M. de Almeida, Sergio Maldonado
cs.LG · physics.comp-ph
Physics-informed neural networks (PINNs) reduce or eliminate the need for large labelled datasets by enforcing governing equations during training. Physics-informed Deep Operator Networks (PI-DeepONets) extend this approach to learning solution operators, enabling rapid prediction across families of problems. Despite these advantages, we show that their application to higher-dimensional problems remains limited by the computational cost of...
-
21
Specification Gaming and a Constrained Reinforcement Learning Mitigation in a Cleaning Gridworld
Hilda Adwubi Osei
cs.LG · cs.AI
Reinforcement learning agents optimize exactly the reward signal they are given, which can diverge sharply from an intended true objective when that signal is only a proxy for it; this failure mode is known as specification gaming. Existing evidence for this failure mode is largely observational, with comparatively few demonstrations pairing a controlled, deliberately constructed proxy/true gap with a mitigation that carries a verifiable...
-
22
Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths
Joran Michiels, Anis Ismail, Maarten De Vos, Alejandro Sifrim
cs.LG · cs.AI
Existing feature attribution methods that account for feature dependencies do not scale to high dimensions. We propose causal integrated gradients (CIG) and causal expected gradients (CEG), which extend integrated gradients to incorporate prior causal structure among input features while retaining its computational efficiency and, under conditions on the causal graph, its axiomatic guarantees. In many settings, some causal structure between...
-
23
Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery
Xudong Zhang, Jianzhe Li, Yitong Tang, Peijie Zhou
cs.LG
Genetic and drug perturbation screens are important tools for elucidating disease mechanisms and validating therapeutic targets, but experimental costs limit the number of candidates that can be tested. Existing perturbation screening methods typically update the surrogate model with feedback while keeping the acquisition function fixed, limiting their ability to adapt selection to different response landscapes. Experimental feedback reveals...
-
24
Scene Reconstruction Using Ubiquitous Wireless Signals via Diffusion Posterior Inference Over physics-Grounded Representations
Vahid Yazdnian, Yasaman Ghasempour
cs.LG
Knowing the layout of the physical world matters for many applications, yet the sensors we rely on for it (e.g., cameras and LiDAR) can fail in darkness, in adverse weather, or behind walls. Wireless signals do not face these limitations: every link between a base station and a user is shaped by the buildings it passes, reflects from, or is blocked by, leaving information about the surrounding scene embedded in the wireless channel measured...
-
25
TIPS: A Tiny Inference-time Policy for Scaling in Diffusion Language Models
Ya-Shi Zhang, Jian Tang, Pierre-André Noël, Oleksiy Ostapenko
cs.LG · cs.AI
Masked diffusion language models expose an inference-time choice: which positions become visible after each denoising pass. Many existing decoding methods use hand-designed rules or require visibility to grow monotonically. We present a $\textbf{T}$iny $\textbf{I}$nference-time $\textbf{P}$olicy for $\textbf{S}$caling ($\textbf{TIPS}$), an approximately $600$K-parameter controller that learns both unmasking and remasking while keeping the...
-
26
Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones
Nathan Chalumeau, Xavier Renard, Remi Meynadier, Hugo Rakotoarimanga, Marcin Detyniecki, Emmanuel de Bezenac
cs.LG · physics.ao-ph
Weather prediction is undergoing an important shift, with data-driven AI models outperforming leading numerical weather prediction systems on average at a fraction of the computational cost. Yet, whether this success extends to extreme events remains contested. Earlier evaluations have exposed important shortcomings, but have largely focused on deterministic models and metrics, leaving the capabilities of the latest probabilistic models less...
-
27
ABNAT: Attention-Based Noise-Aware Training for Robust Transformers on Analog Compute-in-Memory Systems
Wenshuai Yao, Wenyong Zhou, Hanyong Shao, Zhiyuan Ning, Yizhe Chen, Yuannuo Feng, Kechao Tang, Ru Huang
cs.LG
Transformer-based models have become the backbone of a wide range of tasks, but their intensive computation and data movement incur substantial energy overhead. Analog compute-in-memory (CIM) offers an energy-efficient alternative, yet its inherent hardware non-idealities perturb stored weights and can significantly degrade model performance. Although existing noise-aware training (NAT) methods improve robustness by injecting noise during...
-
28
Decoding Naturalistic Speech from fMRI with Temporal Modeling and Multimodal Alignment
Corentin Caris, Louis Jalouzot, Nona Rajabi, Géraud Ilinca, Ahmed Hassayoune, Asilbek Muminov, Thaddée Delebarre,...
cs.LG · cs.AI
Reconstructing what a person perceives from their brain activity is a stringent test of whether neural recordings carry meaningful information. Naturalistic speech offers a rich testbed for this challenge: it unfolds over multiple timescales, but fMRI's noisy, temporally smeared measurements make this structure hard to recover. We introduce NOEMA, a temporal convolutional decoder that aligns windows of consecutive fMRI measurements with...
-
29
Effectiveness of Hidden-State Probes for Localizing Reasoning Failures
Shubham Subhnil, Yannis Belkhiter, Erik Miehling, Adam Dahlgren Lindström, Elizabeth M. Daly
cs.LG · cs.CL
Verifying the final answer of a long reasoning trace may show that the trace is wrong but it does not distinguish three cases. The problem may lie beyond the model's capability, another attempt would succeed, or one step in an otherwise recoverable trace made the trace fail. Standard hidden-state probes are trained on final-answer correctness, a label that conflates these cases. Monte Carlo rollouts distinguish the cases and locate the...
-
30
Momentum, Commentary Tone, and Earnings Surprise in LLM Financial Forecasts
Alina Khaybullina
cs.LG · cs.AI · cs.CL · q-fin.GN
Which inputs drive a language model's financial forecast? We construct synthetic earnings announcements that independently reverse 20-day momentum, non-informational commentary tone, and whether fixed actual EPS beats a manipulated consensus. Six instruction/chat checkpoint conversions from four families (0.49-7.61B base parameters) receive 2,016 prompts each under a direct-answer Q8_0 protocol. The design includes 24 numerical blocks, six...
-
31
Selection Is Not Learning: Choosing Model Futures
Haoyi Yang, Kshitij Mishra, Nils Lukas, Salem Lahlou
cs.LG · cs.AI · cs.CL
Self-evolving language models train on tasks they generate, so every round must decide which updated model the next round inherits. Current loops such as R-Zero, Agent0, and Skill Self-Play make this decision through the task, admitting tasks that look learnable and inheriting every resulting update. We identify a selection-to-update gap in these loops, where a task that looks learnable need not produce a useful update. Most updates on...
-
32
Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing
Adam Deng, Shicheng Liu, Yada Zhu
cs.LG
Multi-agent systems built from frozen language models communicate through text, which discards the internal state the sender already computed and makes the receiver pay to rebuild it. Work on internal channels avoids that cost, framing the problem as transfer: agent A sends information to agent B. Every agent pair that must communicate needs its own transfer bridge, and every agent added to a system needs a new bridge fitted against each...
-
33
Not All Unlabeled Data Are Equal: Unlabeled Data Selection for Semi-Supervised QSAR Modeling with Large Chemical Repositories
Oliver Majer, Saso Dzeroski, Jurica Levatic
cs.LG
Semi-supervised learning (SSL) is particularly attractive in domains where labels are expensive to obtain, while unlabeled examples are readily available. Quantitative Structure-Activity Relationship (QSAR) modeling, which predicts molecular biological activity from chemical structure, is one such domain. Obtaining activity measurements requires costly wet-lab experiments, resulting in small labeled datasets, while chemical repositories such...
-
34
Close Enough is Nowhere Near: Fidelity-Consumability Decoupling in KV Caches
Adam Deng, Shicheng Liu, Yada Zhu
cs.LG
Multi-agent LLM systems communicate in text, which is lossy and wasteful: the sender throws away the reading it already did. A growing literature instead transmits the KV cache, the natural carrier of that reading. We study the most appealing form of the idea: both models stay frozen and the sender's cache is substituted for the reader's with nothing trained. It does not work, and the obstruction belongs to the reader. A frozen transformer...
-
35
GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers
Leo Y. Li-Han, Chris Varghese, Elizabeth B. Habermann, Mark J. Truty, William R. G. Perry, Cornelius A. Thiels,...
cs.LG · cs.AI · eess.SP
Longitudinal electronic health records (EHRs) contain complementary diagnostic and laboratory information about patient health. However, irregularity, sparsity, heterogeneity, and incompleteness in documentation complicate EHR modeling. To address the problem, we introduce GraphBEAT (Graph-based Bucketized Event Aggregation over Time), a temporal graph representation learning framework that groups clinical events into time buckets and...
-
36
Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures
Michał Kozyra, Michael Bronstein
cs.LG
Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks. Existing equivariant tensor encoders require architecture-specific symmetry specifications, while neuron graphs make global attention costly. We introduce a typed graph organized around shared coordinate-permutation actions. Its nodes, called interfaces, represent coordinate spaces whose bound tensor axes must be...
-
37
P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing
Yong Zu, Ninghua Yang, Zezhong Tan, Xinhong Ma, Ziqiang Dong, Yang Yang
cs.LG · cs.CL · cs.CV
End-to-end full-page document parsing must preserve the content and structure of heterogeneous elements, yet otherwise accurate outputs can contain local errors and omissions. A single page-level advantage does not explicitly identify which elements differ in quality across sampled outputs or where their errors occur. We introduce Page-to-Token Policy Optimization (P2TPO), a structure-aligned credit-assignment framework that operates on...
-
38
Learn Only Where You Can't Compute: Structured Corrections to Gaussian Process Posteriors
Tobias Weber, Carla Sagebiel, Philipp Hennig
cs.LG
Physics-informed Gaussian processes (GPs) provide a principled framework for scientific inference by expressing uncertainty over empirical measurements, boundary conditions, and governing equations. However, they struggle to scale to larger datasets and nonlinear information. Conversely, diffusion models excel at learning complex distributions over functions from massive datasets, but struggle in scientific contexts where training data are...
-
39
Time to Fake It: Continual Machine Learning Intensifies Unfairness in Deepfake Detection
Kajaree Das, Oliver Böse, Subarnaduti Paul, Gabriel Storch, Martin Mundt
cs.LG · cs.AI
Deepfake detectors safeguard against misinformation, rendering their failures as much a societal as a technical concern. As generators constantly evolve, detectors trained on static datasets miss newly arising threats, while progressive training interferes catastrophically. Yet, mitigating forgetfulness in terms of accuracy, the prevalent focus of continual learning (CL), is insufficient to reflect real-world impact. We therefore scrutinize...
-
40
Why Shallow Neural Networks Learn Sinusoidal Components First: An Orthogonal Polynomial Dynamics Framework
Yanyang Xiao
cs.LG · cs.AI · math.SP · stat.ML
Neural networks often learn low-frequency components before high-frequency ones --- a phenomenon called spectral bias or termed F-principle. Many numerical studies have demonstrated this phenomenon, and theoretical studies have sought to explain it. However, several goals remain insufficiently addressed: (1) explaining spectral bias asymptotically, including its origin and why the preferred components are generally sinusoidal; (2) extending...
-
41
ChronoSheaf: Joint Spatio-Temporal Spectral Filtering on Cellular Sheaves
Abeer Mostafa, Zahra Ahmadi
cs.LG
Sheaf neural networks generalize graph neural networks by assigning each edge a learned linear restriction map that specifies how the local representations of adjacent nodes relate to one another, thereby mitigating oversmoothing. Existing sheaf architectures, however, define the sheaf Laplacian as an instantaneous spatial operator and therefore cannot explicitly model how signals evolve over time on a graph. We first introduce a spectral...
-
42
The Lagrangian Structure of Cost-Penalized Active Feature Acquisition
Joseph Bingham
cs.LG
Active Feature Acquisition (AFA) sequentially selects features to maximize predictive accuracy under an acquisition budget. A natural heuristic greedily maximizes Expected Information Gain minus a cost penalty, EIG(j|x_S)-lam*c_j (EIG-Cost), but its theoretical guarantees are unclear. We provide an a-posteriori certificate decomposing the gap to the optimal hard-budget policy into a budget-slack term and a greedy-suboptimality term Del_lam....
-
43
The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic Regret
Mohammad Pedramfar, Siamak Ravanbakhsh
cs.LG · math.OC · stat.ML
Many modern learning systems are used not to select a single best action, but to sample diverse high-quality outputs. Examples include entropy-regularized reinforcement learning, RLHF, and reward-guided generative modeling. Motivated by these settings, we study tilted sampling: an online learning problem in which the goal is to sample from the Gibbs distribution induced by an unknown reward function. We define sampling regret as the...
-
44
In-Context Learning Before Specialisation: Theory of Learning in a Solvable Topic Model
Francesco Cagnetta, Casper L. Christensen
cs.LG · cs.AI · stat.ML
Sequence models can generalise in fundamentally distinct ways: extrapolating structures seen in training, or using their prompt to adapt to novel tasks. The prevailing strategy determines how the model behaves beyond its training distribution, controlling potential capabilities and risks. Recent work has characterised many different strategies theoretically, and empirically described the transition between them as the quality and quantity of...
-
45
Self-Calibrated Subspace Robust PCA for Parameter-Free Removal of Mixed Noise and Line Stripes in Hyperspectral Images
Wenzhe Wang
cs.LG
Hyperspectral images (HSIs) are often corrupted by Gaussian noise, impulses and stripes whose intensities vary across bands. The representative coefficient correlated total variation (RCCTV) model restores HSIs efficiently, but it lacks Gaussian and stripe terms, and its noise-aware extensions require the noise level and a stripe budget to be specified in advance. This article proposes a self-calibrated RCCTV (SC-RCCTV) model, in which the...
-
46
Graph Dirichlet Energy for Fitting-Free Bivariate Causal Inference
Povilas Daniušis
cs.LG
We propose the Graph Dirichlet Energy Causal Inference (GDECI) criterion for distinguishing cause from effect in bivariate settings. For a candidate direction $X\to Y$, we construct a kernel similarity graph from $X$ and treat $Y$ as a graph signal. The score is the Dirichlet energy of this signal, induced by the unnormalized graph Laplacian. The reverse score swaps the variables, and the lower-energy direction is inferred as causal. The...
-
47
Learning Lean Feedback for Efficient Proof-Candidate Evaluation on GPUs
Lazar Milikic, Etienne Bamas, Emmanuel Abbe, Viktor Kunčak
cs.LG
Training language models for formal theorem proving requires large numbers of verifier calls. Slow checks and timeouts often leave GPUs waiting and withhold rewards from potentially correct proofs. We train neural evaluators to predict Lean 4 verdicts and compiler feedback on GPUs using 4.84M labelled programs. We compare two validity classifiers with a feedback model that annotates proof attempts with predicted goal states and error...
-
48
Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents
Hanzhen Wang, Boxiang Lyu, Zhongxiang Dai, Siyang Gao, Dake Zhang, Shuang Qiu
cs.LG · cs.AI · math.OC · stat.ML
Risk-sensitive reinforcement learning (RL) addresses decision-making under uncertainty and adverse outcomes. Learning risk-sensitive policies from fixed datasets is important when additional interaction with the environment is costly. Existing work on risk-sensitive RL focuses on online settings or specific risk measures, leaving a general theoretical understanding of its offline setting underdeveloped. In this work, we investigate efficient...
-
49
Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods
Andrea D'Angelo, Francesco Gullo, Davide Mottin, Sayan Ranu, Giovanni Stilo
cs.LG
Graph Unlearning (GU) aims to remove the influence of specific training data from a Graph Neural Network without retraining anew. While most methods address removal of nodes and features, Edge Unlearning (EU), aiming at forgetting edges, has recently attracted dedicated attention as a standalone problem due to the hardness of completely removing the impact of an edge in the model. Despite this, no dedicated benchmark for EU exists besides...
-
50
Physics-Aware Distillation of a Grid Foundation Model for Real-Time Edge Inference
Vlad Alexandru Sănduleac, Shahariya Rasheed Rayamarakkarveettil Puthanpurayil, Noman Khan, Remus Teodorescu
cs.LG
Grid foundation models (GridFMs) are graph transformers pretrained on a masked power-flow objective, and evaluate power flow orders of magnitude faster than an iterative solver. Their size, however, targets data-centre inference, whereas low-inertia operation increasingly asks for inference at the edge, next to the measurement, at batch size one and within a single synchrophasor (PMU) reporting frame. We distil a 20.1M-parameter, 12-layer...
-
51
Local Epochs as Optimal Stopping: Theory and Evidence in Federated Learning
Ke Xiao, Qiyuan Wang, Christos Anagnostopoulos
cs.LG · cs.DC
How long should each client train before communicating? Federated learning usually answers with a fixed, hand-tuned number of local epochs, yet an extra epoch helps only while the loss it removes outweighs the client drift it adds. We cast local training as finite-horizon optimal stopping: a client trains while the next epoch's expected loss reduction exceeds its priced squared drift. We prove that this one-stage look-ahead threshold is...
-
52
A Closed Form Depth-Width Law for Neural Collapse in Deep Linear Networks
Pankhil Gawade, Kirsten Fischer, Guy Wolf, Ewa Szczurek
cs.LG
How depth and width of neural networks shape learned representations is usually studied only after training. We show that, in a tractable feature-learning setting, this dependence can instead be obtained in closed form. Using neural collapse as a probe of representation geometry, we express NC1--NC3 directly in terms of the learned feature kernel, extending an identity known for NC1 to the angular part of NC2 and to NC3 under a ridge readout....
-
53
Measuring the local shape of learning-rate transfer curves
Satoki Ishikawa, Rio Yokota, Ryo Karakida
cs.LG
Understanding the learning-rate (LR) dependence of trained model performance is essential for better optimization of neural networks, but the appropriate size of the LR depends on learning dynamics, architecture, and their hidden biases, and thus our understanding of this complex dependence remains limited. The behavior of the loss curve as a function of the LR has recently been observed in extensive experiments on LR transfer across...
-
54
N-Gram Memories at Two Bits: Quantizing Lookup Tables in Large Language Models
Donghoon Han, Minseop Jung, Dong Woo Kwak, SeungJae Lee, Junhoo Lee
cs.LG · cs.CL
Conditional memory expands language-model capacity through selective lookup, but the full embedding table must remain available for every possible input. We introduce Conditional Program (CP), a compressed representation that reconstructs only the rows an input requests. CP represents each row by a short code and a local scale, with a reconstruction program shared across the table. We instantiate this representation with a Gaussian trellis,...
-
55
Q($γ_H$): Entropy-Guided Horizon Mixing in Multi-Discount Q-Learning
Arwa Albelaihi, Abdulrahman Altahhan
cs.LG
A fixed discount factor in Q-learning imposes a single planning horizon throughout training, despite the differing demands of early exploration and long-term credit assignment. We propose Q($γ_H$), a multi-horizon Q-learning framework that maintains multiple discount-specific heads and adaptively combines them at control time using an entropy-derived confidence signal. The resulting state-dependent mixing weights shift control from shorter-...
-
56
Harmful Partial Interventions and Benign Leakage in Concept-based Models
Gregory Verghese, Christopher J. Soelistyo, Mateo Espinosa Zarlenga, Alessandro Barp, Christopher R. S. Banerji
cs.LG · cs.AI
Artificial intelligence systems deployed in high-risk settings increasingly require models that support meaningful human oversight. Concept-based models (CMs) offer a promising framework by enabling users to inspect and intervene on intermediate, human-understandable concepts. However, concept interventions can counterintuitively worsen downstream predictions, a failure mode we formalise as intervention harm. We distinguish harm after all...
-
57
Pairwise AUC Optimization Needs Corrective Power: A Unified View
Jia Chen, Zhiyong Yang, Shilong Bao, Qianqian Xu, Qingming Huang
cs.LG
Direct pairwise AUC-surrogate training is attractive because it trains toward the ranking metric used at test time, especially under class imbalance. This creates a direct alignment between the training objective and the evaluation metric, but such metric alignment alone does not guarantee that stochastic training remains corrective. We study this gap through Corrective Power: whether pairwise mini-batch updates produce stronger and more...
-
58
Sparse Federated Echo State Networks for Time-Series Classification via Smooth-L1 Regularization
Gengcheng Lyu, Manuel Röder, Frank-Michael Schleif
cs.LG
Echo State Networks (ESNs), as lightweight implementations of reservoir computing, provide efficient solutions for temporal data processing in resource-constrained environments. While standard ESNs offer computational efficiency, their dense readout layers inflate the stored model and the per-sample inference cost. This paper introduces a Smooth-L1 regularized ESN (SL1ESN) that promotes sparsity in the readout layer while preserving...
-
59
FIRM: Fisher-Informed Retention Merging for Federated LLM Unlearning
Reeyansh Shah, Maram Hasan, Subhasis Chaudhuri, Biplab Banerjee
cs.LG · cs.AI · cs.CL
Federated LLM unlearning addresses targeted knowledge removal when forget and retain data remain distributed across private clients and are inaccessible to the server. The resulting locally trained adapters encode conflicting objectives, making their aggregation fundamentally different from conventional federated optimization. A key failure mode is magnitude explosion, whereby unnormalized cross-client aggregation increases the merged update...
-
60
Human Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures
Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
cs.LG · cs.AI · cs.CL
When an LLM agent misbehaves, a human steps in, and that intervention is usually discarded or replayed as training data. We treat it instead as a measurement: a label pointing at the internal computation that failed. We study it in a controlled agent environment, on one failure (asking a clarifying question when the request was already unambiguous), with labels from a rule-based overseer validated against blind human judgment. Claims cover...
-
61
ShiftQAT: Quantization-Aware Training for the Numerical Contract of a Fixed-Function Edge CNN Accelerator
Oguzhan Buyuksolak, Osman Erman Okman, Mehmet Gorkem Ulkar
cs.LG
Fixed-function CNN accelerators make edge inference fast and energy-efficient, but they execute only networks that obey a precise numerical contract. On the MAX7800x family, this contract requires power-of-two, per-tensor, symmetric scales, 8-bit activations and biases, integer-only arithmetic, and one statically configured shift per layer. We present ShiftQAT, the quantization-aware training (QAT) flow we developed for this family, which...
-
62
Router Drift Control: Mitigating Off-Policy Degradation in Mixture-of-Experts Reinforcement Learning
Liangyao Jin, Zhixin Wang, Liming Liu, Mingjun Zhang, Zhengzhou Zhu, Fangcheng Fu, Jinlong Hou, Yuan Cheng, Xiaohe...
cs.LG · cs.AI
Reinforcement learning (RL) can become off-policy due to training-inference mismatch, mini-batch updates, and asynchronous training.The resulting mismatch is especially harmful in Mixture-of-Experts (MoE) models, where rollout--training discrepancies can change routing decisions and lead to router drift. Rollout Routing Replay (R3) mitigates this mismatch by reusing expert selections from the rollout stage during training. Our analysis shows...
-
63
Classical methods for modern applications: synthetic tabular data generation using lightweight discrete response continuous latent variable model
Bartosz Barzdajn, Mateusz Krzysztoń
cs.LG · stat.ML
In this paper, we present a lightweight algorithm for modelling tabular data containing both continuous and discrete variables. The method uses empirical marginal distributions and a selected quantile function to transform the data into a continuous latent space, where a distribution of choice, e.g. a multivariate Gaussian, can be efficiently estimated and applied. While this approach is closely related to classical well-established machine...
-
64
Diffusion Language Models as Open Quantum Systems
Akinori Tanaka, Yukinao Akamatsu, Takuki Tomita, Yuji Hirono
cs.LG · cs.CL · quant-ph
Diffusion language models generate text by reversing a classical diffusion process over token sequences. We show that their continuous-time forward and reverse dynamics can be embedded in the framework of open quantum systems, which describes quantum systems interacting with their environment. This connection provides a basis for extending diffusion sampling to superpositions of sentence states and for modifying the underlying generation...
-
65
Approaching Backpropagation Accuracy with Weight Perturbation on MNIST
Patrick Inoue
cs.LG · cs.NE
Weight perturbation (WP) estimates learning directions from random parameter perturbations and a scalar change in loss, without backpropagating derivatives. We examine how batch size, training duration, and estimator stabilization affect its attainable accuracy in fully connected MNIST networks. In the shallow configuration, large-batch training reaches approximately 97\% test accuracy, compared with an early backpropagation (BP) reference...
-
66
Efficient Pairwise Difference Learning: A Comparative Study of Encoding Strategies and Training Pair Selection
Bernard Georges, Mohamed Karim Belaid, Manuel Rodrigues
cs.LG · cs.AI
Pairwise Difference Learning for Classification (PDC) enhances supervised learning in low-data regimes by training a binary similarity classifier on pairs of instances rather than individual samples, effectively inflating the training set from $n$ to $O(n^2)$ examples. However, the PDC framework leaves critical implementation choices underspecified, particularly regarding input representation and pair selection strategies. This work...
-
67
ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training
Yukun Tian, Junwei Su, Haofeng Xu, Lansong Diao, Zhengping Qian, Weibo Zhao, Wenchao Zhou, Ruiting Zhou, Chuan Wu
cs.LG · cs.DC
Reinforcement learning (RL) has been a critical paradigm for improving large language model (LLM) reasoning and agentic capabilities, but its efficiency remains a major bottleneck. Existing RL systems commonly rely on asynchronous execution to overlap rollout generation with policy optimization for enhanced efficiency. However, this approach faces inherent limitations: mild policy staleness offers only limited training efficiency gains,...
-
68
Local Temporal Contrasts on Human Motion Data Induce a Latent Geometry
Lourenço A. Rodrigues, Felix Putze
cs.LG
Time series such as recordings of human motion data often encode structure across multiple temporal scales, and when a latent state determining this sequence evolves, this structure needs to survive in the representation space for downstream use. Yet the currently prevalent attention-based encoders paired with sequence-level pooling have made single-vector, pointwise comparison the default mode of inference, discarding the trajectory a...
-
69
Market Incentives for AI Safety Investment
Nikita Tsoy
cs.LG · cs.GT · stat.ML
Despite their practical significance, modern AI systems pose significant societal risks, including toxicity, malicious use, and misinformation. Their mitigation depends not only on technical feasibility but also on the incentives of firms that develop and deploy these systems. We show how profit maximization shapes safety investment in an AI supply chain with an upstream LLM provider and several competing downstream firms. In our...
-
70
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Bingxi Hou, Guochao Jiang, Guofeng Quan, Weiqing Li, Wenfeng Feng, Guohua Liu, Yuewei Zhang
cs.LG · cs.CL
Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on student-generated trajectories. However, this endpoint policy shift cannot reveal whether local action preferences evolved consistently during teacher training. The same endpoint shift can result from early and late shifts that reinforce or partially cancel each other. We investigate whether...
-
71
Transfer Learning in Bandits from Unknown Adaptive Policies: Problem-Dependent Lower and Upper Bounds
Adrien Prevost, Timothee Mathieu, Waris Radji, Odalric-Ambrym Maillard
cs.LG
Transfer learning in stochastic multi-armed bandits is typically studied assuming that prior data forms a fixed offline dataset or is generated by a known source. In practice, historical observations come from a previous adaptive decision process whose policy is unknown. We study this setting for bounded rewards in $[0,1]$. Before the online game starts, the learner receives, for each arm $k$, $N'_k$ observations drawn i.i.d.\ from an unknown...
-
72
Learning to Search for Executable Patternmaking from Certified Programs
Zhuotao Xu, Chi Zeng, Liying Yang, Xinxing Yu, Yanyan Liang
cs.LG · cs.AI · cs.GR
Recent models generate sewing patterns from images or text, and program-based representations make these patterns executable. These systems produce a finished pattern and do not model how a patternmaker turns one pattern into another. In practice a new style is made by editing an existing pattern: lengthening the bodice, moving a dart, swapping a sleeve. Pattern archives record the results of such edits and none of the steps. We observe that...
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.