cs.LG · 2026-07-25 · No. 64
Machine Learning, 2026-07-25.
61 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
61 entries-
01
Expanding Flow Maps
Sophia Tang, Pranam Chatterjee
cs.LG
Flow-based generative models have enabled remarkable progress in fast and controllable generation across continuous and discrete state spaces, yet existing parameterizations are constrained to fixed dimensions or fixed sequence lengths. Here, we introduce Expanding Generative Flows (EFlows), which define flows between distributions of increasing dimensionality along an expanding interpolant that grows the state by augmenting it with...
-
02
Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
Hongnan Ma, Yiwei Shi, Mengyue Yang, Weiru Liu
cs.LG · cs.AI
Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserve a black-box model's prediction, but also necessary for maintaining it. However, existing sufficiency-oriented methods can assign high importance to spurious subsequences that support the prediction without being essential to the model's decision. We introduce \textbf{TimePNS}, a necessity-aware framework for time-series...
-
03
Graph Learning on Ensembles of Cyclic Peptides: An Investigation of Molecular Ensemble Modeling
Aaron Feller, Kris Deibler, Maxim Secor
cs.LG · q-bio.BM
Molecular property prediction from structure often uses a single representative conformation, even though many molecules exist as conformational ensembles in solution. We introduce EnsembleEGNN, a molecular ensemble foundation model that encodes an ensemble by first encoding each conformer with shared Equivariant Graph Neural Network (EGNN) layers, then pooling the resulting conformer representations with a Set Attention Block. We pretrain...
-
04
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
Dongjie Fu, Di Cao, Xize Cheng, Zihan Zhang, Wenxu Jia, Yifu Chen, Shengpeng Ji, Yu Zhang, Tao Jin
cs.LG
While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this gap, we propose X$^3$-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student. During training,...
-
05
Zero-Flow Two-Sample Tests
Yakun Wang, Leyang Wang, Song Liu, Taiji Suzuki
cs.LG · stat.ML
We propose a new approach to two-sample testing for deciding whether two sets of samples are drawn from the same distribution. The test is built on a statistical discrepancy based on the zero-flow criterion, termed zero-flow discrepancy (ZFD). We prove the validity of ZFD and propose a practical testing procedure, termed the zero-flow two-sample test (ZF2ST). The key idea is to learn how samples from the two distributions are locally...
-
06
Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context
Alagappan Valliappan
cs.LG · cs.CL · cs.PF
Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP/NEXTN) draft head under the assumption that the draft is negligibly cheap. At million-token context this breaks: an MTP draft head typically runs full attention over the entire KV cache at every draft step, so its read grows linearly with...
-
07
Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
Gil Lifshits, Igal Bilik, Gilad Katz
cs.LG · cs.AI · cs.MA · cs.RO
Coordinating autonomous vehicles at unsignalized intersections remains a critical challenge for multi-agent reinforcement learning (MARL) systems, which typically struggle with combinatorial action spaces, reliance on privileged information, or rigid agent designs. We propose Master-Agent Proto-plan System (MAPS), a hierarchical deep reinforcement learning (DRL) architecture in which a centralized Master agent generates a compact, continuous...
-
08
Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design
Martin Anthony, Kaveh Salehzadeh Nobari
cs.LG · stat.ML
An initial high-recall stage in an empirical pipeline decides which items pass to later review, labelling, or modelling, and relevant items it misses are lost to every subsequent stage. We study how many audit labels are needed to certify, with finite-sample validity, that this missed relevant mass is small, and our main results characterise the label complexity of this problem. We first show that no procedure using only labels from inside...
-
09
Error Certificates for KV-Cache Eviction via Randomized Design
Peng Xie
cs.LG · cs.AI · cs.CL
Deterministic KV-cache eviction keeps the top-$k$ tokens under an importance score and deletes the rest. We prove that this design cannot know what it destroyed: evicted values can be altered so that everything the serving system retains is unchanged while the true attention-output error grows arbitrarily, so no serving-time estimator of that error is consistent. Randomized eviction restores identifiability. With a Poisson-sampled tail at...
-
10
Test-Time Scaling via Error Localization
Rajiv Shailesh Chitale, Rahul Madhavan, Taneesh Gupta, Deepanway Ghosal, Aravindan Raghuveer
cs.LG
Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks. However, standard approaches such as independent sampling and sequential multi-turn refinement operate without token-level credit assignment, resulting in computational inefficiency, since valid reasoning prefixes are frequently discarded. In this work, we introduce Test-Time...
-
11
KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
Yann Bouquet, Alireza Khodamoradi, Kristof Denolf, Mathieu Salzmann
cs.LG · cs.CV
Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent. The standard fix applies an invertible linear transform to the activations and its inverse to the weights before quantizing both. Normalization layers between blocks force this transform to run online at every denoising step, making its...
-
12
Context-weighted Discrete Flow Matching
Daniil Cherniavskii, Daniel Severo, Karen Ullrich
cs.LG
Discrete flow matching provides a flexible framework for generative modeling on discrete structures. However, the standard factorized training objective exposes the model to targets of varying difficulty, mixing well-conditioned, predictable tokens with ambiguous, high-entropy ones. We empirically demonstrate that the uncertainty over the value of each token is closely related to the density of available context in its neighborhood. Motivated...
-
13
Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
Ahmad Halimi Razlighi, Maximilian H. V. Tillmann, Edgar Beck, Bho Matthiesen, Armin Dekorsy
cs.LG · cs.IT · eess.SP · stat.ML
Cooperative multi-task semantic communication (CMT-SemCom) improves task execution performance by leveraging shared representations. However, as we demonstrated in [1], cooperative multi-tasking can be either constructive or destructive, depending on the semantic relationships among tasks. To ensure constructive cooperation, we propose a semantic-aware task clustering method for CMT-SemCom. We have formulated a sequential multi-stage...
-
14
A Diffusion-Model Subpopulation Digital Twin for Mobile Health Deployment: A Case Study on the HeartSteps Intervention
Ziping Xu, Yuyi Chang, Chenshun Ni, Nithin Sugavanam, Asim H. Gazi, Pedja Klasnja, Emre Ertin, Susan A. Murphy
cs.LG · stat.ME
Mobile-health interventions increasingly use online learning and decision making algorithms to personalize when to nudge users toward healthier behavior, but a poorly designed algorithm can burden and disengage participants. New algorithm design decisions should therefore be vetted against realistic simulated users before each real-life deployment. We propose a method to develop ``JITAI-Twins'': digital twins of a target subpopulation for...
-
15
Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy
Jingyuan Li, Xiaoyi Jiang, Yixuan Jiang, Wei Liu, Yi Zhu, Zuoqiang Shi, Pipi Hu
cs.LG · cs.AI
Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios. While positivity guarantees nonnegative reverse jump rates, it does not ensure Bayes realizability: ratios at a noisy state need not be jointly induced by any clean-token posterior under the forward kernel. The score-entropy loss has the correct population optimum but does not enforce this constraint away from it. In a...
-
16
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
Hossein Mobahi, Peter L. Bartlett
cs.LG · cs.AI · stat.ML
Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge. Given the link between learning and compression, network compression offers a promising lens to analyze this knowledge. However, standard compression heuristics often suffer from scale symmetries and architectural biases. To resolve these, we introduce Hilbert Operator for Progressive Encoding (HOPE), a mathematical framework...
-
17
Emergent Misalignment Recruits a Pre-existing Persona Subspace
Mohammed Suhail B Nadaf
cs.LG
Fine-tuning an aligned language model on a narrow stream of bad advice can make it broadly misaligned on questions unrelated to the training data, a phenomenon called emergent misalignment. We ask why the narrow lesson generalizes at all, and we find that narrow fine-tuning recruits a persona structure that is present in the model before the fine-tune exists. From a frozen instruction-tuned model (Qwen2.5-14B-Instruct) we extract per-domain...
-
18
Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning
Billel Habbati, Alessio Merlo, Luca Verderame, Meriem Guerar
cs.LG
Machine unlearning aims to remove the influence of specific training data while preserving model utility. Many state-of-the-art approaches pursue this goal by restricting the forgetting update to a subset of parameters selected through gradient-based saliency. Although such methods are widely adopted, the actual contribution of saliency-based weight selection to representation-level forgetting remains unclear. In this work, we perform the...
-
19
How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning
Kaizhen Tan, Heqing Du, Yang Feng
cs.LG
A LoRA adapter is a few megabytes that almost everyone treats as a skill rather than a record of the data behind it. We put that assumption on a scale. Extending compression-based memorization analysis to the frozen-base setting, we measure directly, in bits, how much a low-rank adapter writes into a model it never changes. The answer is both smaller than full fine-tuning and less lawful than parameter counting would predict. Adapters store a...
-
20
M$^3$-Gen: Interpretable Multimodal Generation of Gene Expression Profiles Using Clinical and Imaging Data
Francesca Pia Panaccione, Carlo Sgaravatti, Marco Venere
cs.LG · cs.AI · cs.CV
Integrating heterogeneous biomedical data, including clinical metadata, histopathology images, and molecular profiles, is crucial for comprehensive disease understanding. However, gene expression data acquisition remains constrained by high costs and privacy concerns, limiting its use in multimodal research and AI-driven applications. We present MultiModal Molecular Generation (M$^3$-Gen), a novel framework for the generation of gene...
-
21
AI Assistants Overassist
Verona Teo, Raghav Jain, Tobias Gerstenberg, Max Kleiman-Weiner
cs.LG · cs.AI · cs.CL · cs.CY · cs.HC
Large language models (LLMs) are increasingly used as tutors and thought partners, helping users reason through problems. While guidance from AI assistants can scaffold thinking and foster learning, such benefits depend on how they help--for instance, intervening too early or too frequently may hinder true learning and cognitive engagement. Yet how AI systems navigate intervention decisions during problem-solving remains poorly understood....
-
22
Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning
Jonas Peché, Aliaksei Tsishurou, Alexander Zap, Günter Wallner
cs.LG · cs.AI
Multi-task learning (MTL) is a promising approach for prediction tasks derived from video game state data, as modern game telemetry provides multiple related supervision signals from the same structured observations. We study whether a shared model trained jointly across tasks in team-based multiplayer games can improve generalization while reducing training and inference cost compared to specialized single-task models. We adapt a multimodal...
-
23
The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and What Actually Works
Yu Wang
cs.LG
Dense per-step supervision is an appealing remedy for sparse-reward, long-horizon LLM agents: reward the agent for predicting its next observation, and memory should follow. We show that under group-normalized RL (GRPO), this recipe does not merely fail -- it destroys the policy. Across Qwen3-1.7B/4B/8B on ALFWorld, a potential-based prediction reward drives every run into a degenerate absorbing state (prediction accuracy -> 1.0, task success...
-
24
Filter Learning for Subgraphs: Algebras and Performance Risk Bounds
Purui Zhang, Feng Ji, Yanan Zhao, Bihan Wen, Wee Peng Tay
cs.LG · eess.SP
Graph signal processing tasks that leverage spectral information typically assume access to the complete graph topology, which is often unavailable in practice. We propose a systematic framework for subgraph filter learning (SFL), where subgraph-supported operators approximate ambient graph filters under partial observations. We formulate SFL as a statistical learning problem in which optimal subgraph operators are inherently data-dependent....
-
25
Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines
Irena Girshovitz, Dan Zeltzer, Ran Gilad-Bachrach
cs.LG
While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes successfully yet relies on invalid causal assumptions. We present the Artificial Intelligence (AI)-based Epidemiology Research Assistant (ARA), a framework that makes these failures visible by explicitly encoding causal design principles, study-specific assumptions, and methodological...
-
26
Agree on the Model, Verify the Inference: GKR Protocols for HND-Based Transformer Inference
Xiaolong Liang, Juanjuan Li, Rui Qin, Yisheng Lv
cs.LG · cs.CR
Outsourced Transformer inference exposes clients to model substitution and incomplete execution, while direct replay removes the computational benefit of delegation. We present GKR-HND, a registered-model protocol for verifying the polynomial backbone of Homomorphic--Nonhomomorphic Decomposition Transformers. The retained verifier checks the GKR transcript and registered-weight openings, but delegates expensive public evaluations to an...
-
27
Demographically-Informed Heat-Mortality Risk Curves via Risk Graph Neural Networks
Alex O. Davies, Eunice Lo, Rui Zhu
cs.LG · cs.AI
Estimating heat-related mortality risk is a core task in environmental epidemiology, typically addressed with Distributed Lag Non-linear Models (DLNMs); interpretable exposure-response surfaces fitted to temperature-mortality time series. DLNMs are effective but ignore demographic and geographic context, despite well-established relevance to heat vulnerability. We propose Risk Graph Neural Networks (RGNNs), a hierarchical GNN encoder that...
-
28
Relative Value Learning
Marc Höftmann, Jan Robine, Stefan Harmeling
cs.LG · cs.AI
In reinforcement learning, critics typically estimate absolute state values $V(s)$, estimating how good a particular situation is in isolation. However, it turns out that only differences in value are relevant for control. Motivated by this, we propose Relative Value Learning (RV), a framework that learns value differences directly via an antisymmetric function $Δ(s_i, s_j) = V(s_i) - V(s_j)$. We introduce a pairwise Bellman operator and...
-
29
GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Diabetes
Davide Marelli, Giorgia Rigamonti, Mirko Paolo Barbato, Paolo Napoletano
cs.LG · cs.AI
Preprocessing blood glucose time-series data is a critical yet often overlooked step in developing data-driven methods for diabetes management, particularly for type 1 diabetes. The lack of standardized preprocessing workflows and evaluation protocols hinders reproducibility and complicates fair comparison across studies. These challenges are further exacerbated by data-sharing restrictions, as privacy and licensing constraints often prevent...
-
30
TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning
Chaofan Pan, Lingfei Ren, Xiangyu Jiang, Yanhua Li, Xuemei Cao, Xiangkun Wang, Hao Yu, Wei Wei, Xin Yang
cs.LG · cs.AI
Offline Reinforcement Learning (RL) agents are trained on fixed behavioral trajectories, which makes trajectory-level deletion important when selected data must be removed after training. Evaluating such deletion is difficult because a lower membership score can reflect trajectory removal, residual memorization visible to another attack, or policy collapse that destroys useful behavior. We introduce Trajectory-level memOrization and...
-
31
Smooth Neural Point Processes via B-Splines
Michele Bellomo, Riccardo Ramaschi, Alberto Dolara, Tomaso Aste
cs.LG · stat.ML
Temporal point processes (TPPs) provide a general and flexible framework for modeling sequences of events in continuous time. Neural networks have been successfully employed to model TPPs in a highly expressive and data-driven way. Neural TPPs are typically trained via Maximum Likelihood Estimation (MLE) by minimizing the negative log-likelihood (NLL), which depends on both the conditional intensity function (CIF) and its integral over time,...
-
32
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
Bizu Feng, Zhimu Yang, Shuming Wang, Shaode Yu, Yuan Cheng, Xiaojun Qian, Zixin Hu
cs.LG
We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradients provide an axiomatic formulation of attribution, but their practical use in deep GNNs typically relies on finite-sample numerical approximations to the path integral, requiring a trade-off between quadrature error and computational cost. This paper proposes APEX,...
-
33
Training Large Language Models for Self-Explanation Faithfulness
Yeoktatt Cheah, María Pérez-Ortiz, Noah Y. Siegel, Oana-Maria Camburu
cs.LG · cs.AI · cs.CL
We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated reasoning accurately reflects its internal decision-making process. While existing work focuses on evaluating faithfulness or using inference-time prompting frameworks to improve an LLM's self-explanation's tractability, these approaches do not provide a mechanism to directly optimize a model's...
-
34
CASC: Causal Adversarial Subspace Clustering for Multivariate Spatiotemporal Data
Francis Ndikum Nji, Vandana Janeja, Jianwu Wang
cs.LG
Deep subspace clustering plays a critical role in applications involving multivariate spatiotemporal data, such as sea ice monitoring, disease spread analysis, and tracking neuro-degeneration over time. Despite recent advances, existing methods primarily rely on geometric self-expressiveness, assume static subspace structures, and often fail to capture causal dependencies, local spatial interactions, and long-range temporal dynamics inherent...
-
35
Nipping the Butterfly Effect in the Bud: Self-Output Fine-Tuning for Autoregressive Weather Prediction
Yun-Ye Cai, Hsuan-Tien Lin
cs.LG
Long-horizon weather forecasting is a fundamental challenge in atmospheric science, for which autoregressive Deep Learning Weather Prediction (DLWP) has emerged as the primary paradigm. Although the autoregressive pipeline is highly scalable and flexible, its prediction errors grow rapidly over long forecasting horizons. In this work, we study this error growth phenomenon from both theoretical and empirical perspectives. Our analysis reveals...
-
36
Spectral Transformation for Layer-wise Global Rank Discovery in Federated LoRA for Vision Transformers
Hariharan Ramesh, Jyotikrishna Dass
cs.LG · cs.DC
Fine-tuning Vision Transformers (ViTs) with low-rank adapters (LoRA) promises better communication efficiency under federated setup, yet existing aggregation strategies face fundamental limitations. Independently averaging these LoRA factors is mathematically inconsistent, introducing cross-term aggregation error. In contrast, approaches that preserve heterogeneous client ranks by concatenating local adapters on the server substantially...
-
37
From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python
Muntasir Adnan, Manile Srun, Carlos C. N. Kuhn
cs.LG
The original ALPHA benchmark introduced a taxonomy-aware penalty for evaluating CWE-level vulnerability prediction in Python and proposed that the penalty could theoretically also serve as a training signal. This paper provides that validation. We compare three delivery mechanisms: supervised fine-tuning, a dual-head classification loss, and reinforcement learning with a dense reward derived from the normalised penalty. We find that...
-
38
Counterfactual Explainability Framework With CycleGAN And Counterfactual-Classifier Alignnment Score for Retinal Disease Classification
Kritanu Chattopadhyay, Sayanjit Singha Roy, Soumya Chatterjee
cs.LG · cs.CV
Automated detection of vision impairing retina-based ocular conditions from fundus images is important for early screening, timely referral and reducing dependency on specialist-only assessment, for which neural network-based deep learning (DL) models have been widely utilized. However, explainability of the DL frameworks remains a major bottleneck for clinical adoption, particularly when model decisions are not linked to retinal regions that...
-
39
Regularized Optimization on Grassmann Manifold: Theory, Algorithm and Applications
Zhuan Liang, Zheng Zhai
cs.LG
Spectral methods are among the most widely used techniques for community detection, clustering, and graph learning. Their performance, however, critically depends on the accurate estimation of the underlying spectral subspace and can deteriorate substantially in the presence of noise, outliers, or model perturbations. To address this limitation, we propose a Regularized Projection Matrix Approximation (RPMA) framework for robust estimation of...
-
40
Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay
Xiaolong Li, Zhangchen Zhou, Zhi-Qin John Xu
cs.LG · cs.NE
Most explanations of training instability focus on \emph{learning-rate criticality}, typically characterized by the Edge of Stability, beyond which optimization becomes unstable. We argue that, in practical deep neural network training, there is an additional and often overlooked \emph{weight-norm criticality}. This criticality is induced by the interaction between normalization (which introduces scale-invariant components) and weight decay...
-
41
ADABORD: a novel AdaBoost approach for ordinal classification
Rafael Ayllón-Gavilán, Francisco José Martínez-Estudillo, David Guijo-Rubio, César Hervás-Martínez, Pedro A. Gutiérrez
cs.LG
Ordinal Classification (OC) deals with classification tasks where the classes follow a natural order. Despite the progress in OC, many existing approaches fail to fully leverage the ordinal information, treating the problem as nominal classification and thereby losing performance potential. In this work, ADABORD, an AdaBoost framework specifically designed for ordinal classification problems, is introduced. The ordinal nature of the classes...
-
42
The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning
Ishan S. Kshirsagar
cs.LG · cs.CL
Latent, or silent, reasoning lets language models carry out intermediate computation in continuous vector space instead of words, and is widely assumed to function as an internal scratchpad the model actively consults during inference. Whether that assumption survives reinforcement learning has not been tested directly: existing causal analyses of latent reasoning are confined to math and logic tasks, and compare a model's reliance on its...
-
43
Best-of-Evidence: Best-of-N Selection under Partial Verification
Cenwei Zhang, Teng Fang, Yuxia Wang, Derek Li, Bryan Dai, Lei You
cs.LG
BoN improves model outputs by sampling several candidates and selecting one with a proxy score, but it assumes that complete candidates can be evaluated reliably. Many vision-language tasks instead provide only partial verification: a finding, span, value, region, or relation may be checkable even when no dependable whole-response verifier exists. Moreover, the same claim may recur across candidates with opposing stances, allowing one...
-
44
Three-Pronged Spectral Control for Federated Parameter Efficient Fine Tuning
Shiva Raj Pokhrel, Dipsan Bhattarai, Anwar Walid
cs.LG · cs.NI
Federated parameter-efficient fine-tuning (PEFT) enables communication-efficient adaptation of large pretrained models on decentralized edge data, but it remains fragile under non-IID client heterogeneity. In low-rank adaptation (LoRA), different clients may learn locally useful but spectrally misaligned update subspaces, causing high-variance aggregation and poor global transfer. We propose TRISHUL, a spectral-control framework for robust...
-
45
Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation
Quazi Ishtiaque Mahmud, Nesreen K. Ahmed, Ali Jannesari
cs.LG · cs.AI
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code. In this work, we propose CudaPerf, a reflective RL...
-
46
HierarchicalDAEW: Domain-Aware Edge-Weighted Graph Convolution with Evidential Uncertainty for Multi-Section Spatial Gene Expression Prediction from H&E Histology
Kritanu Chattopadhyay, Soumya Chatterjee, Ondrej Krejcar, Debotosh Bhattacharjee
cs.LG · q-bio.GN
Spatial transcriptomics assays remain costly and technically demanding, restricting transcriptome-wide profiling to specialist settings and preventing routine clinical deployment. Predicting spatially resolved gene expression from H&E histology could close this gap, yet current methods largely ignore the underlying tissue architecture and rarely quantify how their predictions can be trusted. We introduce HierarchicalDAEW, a dual-graph...
-
47
Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries
Hyeong-Gun Joo, Songnam Hong, Dong-Joon Shin
cs.LG
On-device federated learning (FL) enables privacy-preserving and personalized model training on resource-constrained devices such as smartphones and IoT nodes. To reduce communication cost, sign-based methods (e.g., signSGD) transmit one-bit gradients. However, exposing gradient signs makes them vulnerable to inference attacks, while existing secure aggregation schemes are often incompatible with such methods or incur significant...
-
48
TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging
Ting Gong, Shitan Xu
cs.LG · cs.AI · math.AG
Model merging combines independently trained or fine-tuned models, but pairwise alignability does not imply globally consistent alignment. We formulate merging as a finite descent problem in which checkpoints are local objects, alignment maps are transitions, and cycle products are residuals. TwistedMerge is a conservative certification pipeline that separates fixed-chart averaging, synchronization-removable gauge inconsistency, a certified...
-
49
Position Bias is Hidden Behind Ceiling Effects: A Permutation Diagnostic for LLM Benchmarks
Hiroki Tamba
cs.LG · cs.CL
Position bias in multiple-choice LLM evaluation is widely cited as a confound in capability comparisons, but published measurements rely on single answer-order shuffles whose results confound the bias signal with content-level noise and sampling stochasticity. I introduce inspect_permute, an open-source extension to the inspect_ai evaluation framework that runs exhaustive answer-order permutations per question and reports the chi-squared /...
-
50
Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery
Amirhossein Nouranizadeh, Sarang Rajendra Patil, Alan John Varghese, Varsha Narayanan, Amit Chakraborty, Mengjia Xu
cs.LG · cs.AI
Scientific machine learning methods such as neural operators and physics-informed neural networks have advanced engineering applications and inverse problems, but their training typically requires large volumes of simulated data. This makes data preparation and model training expensive. We propose Graph Wavelet Compressed Sensing (GWCS), a learning-based framework for offline compression of graph signals by representing them as sparse,...
-
51
Offline RL with Hierarchical Action Chunking
Ahad Jawaid
cs.LG
Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets. However, scaling these methods to long-horizon tasks remains a challenge due to the curse of horizon, where value estimation errors can compound through long chains of bootstrapped Bellman backups. Existing hierarchical approaches mitigate this by decomposing tasks into subgoals, yet they often rely on low-level...
-
52
Beyond Heavy Log Curation: Perplexity-Based APT Detection via Unsupervised, Context-Augmented Language Models
Shoya Otsu, Kei Suzuki, Toshiaki Koike-Akino, Jing Liu, Ye Wang
cs.LG · cs.AI · cs.CL · cs.CR
Advanced Persistent Threats (APTs) remain difficult to detect because only a small fraction of events in large-scale logs are attack-related, and investigation is expensive and hard to scale. Prior machine-learning approaches can reduce analyst workload, but they often rely on heavily curated training data and sophisticated preprocessing pipelines. Building and maintaining such pipelines require substantial domain expertise and engineering...
-
53
Robust Asynchronous Q-Learning under Reward and State Corruption via Batching
Sreejeet Maity, Aritra Mitra
cs.LG · eess.SY
Motivated by reinforcement learning in harsh environments, we consider the problem of learning an optimal policy subject to adversarially corrupted feedback. Specifically, at each time-step, an adversary can perturb both the reward and state observations of the learner following the Huber contamination model. To defend against such data corruption, we propose {\texttt{BR-Async-Q}}: a novel, epoch-based, robust \(Q\)-learning algorithm built...
-
54
New Complexity-Theoretic Frontiers of Tractability for Neural Network Training
Cornelius Brand, Robert Ganian, Mathis Rocton
cs.LG · cs.DS
In spite of the fundamental role of neural networks in contemporary machine learning research, our understanding of the computational complexity of optimally training neural networks remains incomplete even when dealing with the simplest kinds of activation functions. Indeed, while there has been a number of very recent results that establish ever-tighter lower bounds for the problem under linear and ReLU activation functions, less progress...
-
55
External Clustering Validation by the Homogeneity-Parsimony Trade-off
Andreas Tiffeau-Mayer
cs.LG · cs.IT · stat.ME
Scalar metrics are often used to evaluate clusterings against known classes, but they can obscure a fundamental trade-off: clusterings should be informative about class labels while avoiding unnecessary fragmentation. Here we describe normalized scores of cluster homogeneity and parsimony that quantify this trade-off. These scores build on the information bottleneck principle, modified to not reward lossy compression. We show by example and...
-
56
Memoir: Should a Model Write to Its Memory While It Thinks?
Jaber Jaber, Osama Jaber
cs.LG · cs.NE
Memoir combines per-sample fast memory, shared slow parameters, variable-depth latent recurrence, and a future-latent energy objective. We test its riskiest coupling: each pondering iteration may rewrite the fast tier that the same iteration reads. On procedural associative recall with key interference, we compare a coupled arm against an otherwise identical read-only pondering arm. Both arms contain 81,738 parameters, including 76,362...
-
57
Synthetic minority data is redundant or invalid: a data-dependent validity theory and a de-biased test
Ahmad B. Hassanat, Ahmad S. Tarawneh, Ghada A. Altarawneh
cs.LG · cs.AI
For two decades, the standard remedy for class-imbalanced learning has been to fabricate synthetic minority examples, and the standard evidence of their validity has been a check that cannot fail: synthetic points are scored against the very data that generated them. We de-bias the check. Validity becomes a population quantity -- the probability that a synthetic point truly belongs to the minority class -- with a consistent estimator that...
-
58
Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry
Jason Y. Hu, Ivan Higuera-Mendieta, Patrick Obin Sturm, Makoto M. Kelp
cs.LG · physics.ao-ph
Weather forecasting foundation models (FMs) are increasingly fine-tuned to predict air quality, offering fast global pollution forecasts at lower computational cost than conventional chemical transport models. These FMs are typically trained on reanalysis data and generate forecasts through autoregressive rollout. They do not explicitly represent governing physical or chemical processes. Therefore, high forecast skill does not reveal whether...
-
59
Memory-Computation Tradeoffs in Semi Amortized Parametric Optimization
Shijie Pan, Agustin Castellano, Zeyu Shen, Enrique Mallada
cs.LG
Learning-enabled decision systems often use offline data or computation to reduce online compute cost. Despite the empirical success of such approaches, there is limited general understanding of how much offline information is needed to achieve a desired accuracy under a fixed online computation budget. We study this question through the lens of amortized parametric optimization: an offline phase stores a finite memory of solved problem...
-
60
GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries
Miguel P. Bento, João Seabra
cs.LG · cs.CL
Transformers are known to have internal continuous symmetries that leave outputs invariant, while modifying quantization. GaugeQuant leverages this in-training by introducing a LogSumExp term to the loss that breaks the symmetries, thus selecting a basis that minimizes activation outliers. A stop-gradient operator ensures that only rotation matrices are updated, yielding the language modeling objective completely unaltered. Our requires no...
-
61
Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion
Mohammad Raahemi, Ali Sekhavati, Alireza Maleki, Hamid Nasiri
cs.LG
Multimodal learning is a robust approach to improve predictive performance in applications such as medical prognosis. However, the clinical applicability of models that use multimodal learning is hampered by their poor performance under noisy or uninformative data streams. Present fusion approaches often lack robust mechanisms for the dynamic assessment of data quality and for the provision of a trustable confidence score on the final...
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.