cs.LG · 2026-06-25 · No. 34
Machine Learning, 2026-06-25.
63 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
63 entries-
01
RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments
Babak Rahmani, Sebastian Dziadzio, Joschka Strüber, Sergio Hernández-Gutiérrez, Matthias Bethge
cs.LG
For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention. We pose a computational analogue: given only behavioral traces of an agent in a game environment, can a learner reconstruct the underlying decision program as executable code, and how much does this reconstruction improve...
-
02
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
Andrei Liviu Nicolicioiu, Mohammad Pezeshki, Aaron Courville
cs.LG · cs.AI
On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a correct demonstration to provide dense token-level feedback. We show that this could come at a hidden cost: rollout diversity decreases and pass@k curves flatten (i.e., generating more rollouts fails to improve accuracy). We trace this to compounding biases in the design of self-distillation with...
-
03
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Changdae Oh, Wendi Li, Seongheon Park, Samuel Yeh, Tanwi Mallick, Sharon Li
cs.LG · cs.AI
Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environment feedback make both human annotation and Monte Carlo estimation infeasible at scale. In this work, we show that reinforcement learning (RL) post-training already provides the ingredients for effective step-level scoring,...
-
04
Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment
Aditya Singh, Gerson Kroiz, Senthooran Rajamanoharan, Neel Nanda
cs.LG · cs.AI
A central goal of safety research is determining whether a model is misaligned. Prior work has largely focused on detecting concerning behavior. But behavior alone does not establish misalignment: a concerning action can arise from benign causes such as confusion. This motivates model forensics: investigating whether the action was driven by malign intent. In this paper, we propose a baseline protocol for model forensics consisting of two...
-
05
Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining
Juliana Li, Diya Sreedhar
cs.LG · cond-mat.dis-nn · cs.AI · cs.CL
Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0.94 by step 925). By step 3,500 the same model scores near zero on the same probes, although the rule's evidence is still in the training data. We call this within-run reversal natural ungrokking: the corpus decides, with no...
-
06
Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization
Philipp Grohs, Davide Nobile
cs.LG
Variational Monte Carlo (VMC) is a central algorithm in electronic structure theory and has gained renewed importance through modern neural-network ansätze such as FermiNet. At its core, VMC seeks ground states by minimizing the Rayleigh quotient by stochastic optimization. In this work, we show that the resulting stochastic optimization problem is intrinsically governed by the nodal geometry of the underlying wave function. More precisely,...
-
07
Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization
Kamar Hibatallah Baghdadi, Kawther Guoual Belhamidi, Sara Belhadj, Aissa Boulmerka, Nadir Farhi
cs.LG · cs.AI · math.OC
We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks. The framework decomposes the compression search across two levels of abstraction: low-level agents (LLAs) operate independently per block, selecting per-kernel configurations over a multi-discrete action space spanning bitwidth, pruning keep-ratio, quantization type, and granularity,...
-
08
The Inference-Compute Frontier and a Latency-Efficient Architecture for Limit Order Book Prediction
C. Evans Hedges
cs.LG · q-fin.ST · q-fin.TR
We study whether a scaling-law-style inference-compute frontier appears in limit order book prediction. Using FI-2010 and a suite of models ranging from small decision trees to neural LOB architectures, we find that the realized empirical frontier of predictive loss versus structural forward work is well summarized by a power law. In particular, with MLPLOB held out as an architecture family, a power-law fit to the low- and mid-compute...
-
09
Tensorion: A Tensor-Aware Generalization of the Muon Optimizer
Vladimir Bogachev, Vladimir Aletov, Alexander Molozhavenko, Sergei Kudriashov, Maxim Rakhuba
cs.LG · cs.CV · math.NA
Common first-order optimizers, such as Adam, implicitly treat each parameter block as an unstructured vector, which disregards the multilinear weight structure present in many modern machine learning models. Recent work has shown that exploiting matrix structure can improve optimization dynamics. A notable example is Muon, which performs steepest descent under the spectral norm constraint. We take the next step and introduce Tensorion, a...
-
10
Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors
Alexander Hägele, Alejandro Hernández-Cano, Atli Kosson, Martin Jaggi
cs.LG
Modern neural network training relies on optimizers such as Adam and Muon which act on each weight matrix as a single object. Yet every weight matrix carries two distinct quantities -- a \emph{magnitude} and a \emph{direction} -- and all optimizers stepping in the matrix as a whole couple their dynamics: the directional change from an update depends on the current magnitude, while the magnitude drifts as a byproduct of learning the direction,...
-
11
$\text{DT}^2$: Decision-Targeted Digital Twins
Harry Amad, Mihaela van der Schaar
cs.LG
A digital twin (DT) is a virtual model of a real-world system that can assist decision-making by simulating scenarios induced by different policies. However, typical machine learning-based DTs do not optimise for this use case. We prove that, when model capacity is limited, training DTs to minimise one-step transition errors can produce suboptimal models for ranking sets of policies according to a reward function. We further show that this...
-
12
Variational Autoencoder Layer
Gananath R
cs.LG
Variational Autoencoders (VAEs) belong to a family of autoencoders with probabilistic properties, making them well suited for generating data by producing a smooth and continuous latent space. Despite being introduced over a decade ago, the method continues to be widely adopted in both research and industry for diverse applications. While VAEs are typically used as standalone models, this paper introduces a novel approach to integrate them as...
-
13
An Analysis of Posterior Collapse, Parameterization and Initialization in Variational Deep Gaussian Processes
Francisco Javier Sáez-Maldonado, Juan Maroñas, Daniel Hernández-Lobato
cs.LG
DGPs are probabilistic models with remarkable prediction performance that concatenate GPs across several layers. Exact inference in DGPs is intractable, and variational inference is often used to approximate the posterior with a parametric distribution tuned by minimizing the Kullback-Leibler divergence. Moreover, finding a good VI approximation is challenging. In particular, a problem of VI is posterior collapse, where VI converges to a...
-
14
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents
Peng Xu, Sijia Chen, Junzhuo Li, Xuming Hu
cs.LG · cs.AI
Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes. However, this ties a step's credit to its rollout's final outcome: semantically near-identical intermediate steps receive opposite credit depending on whether their trajectory eventually succeeded or failed. Such semantic credit inconsistency sends conflicting gradients to similar...
-
15
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
Ke Zhao, Zixiang Di, Hong Qian, Xiang Shu, Yaolin Wen, Qitao Shi, Bingdong Li, Xingyu Lu, Xiangfeng Wang, Jun Zhou,...
cs.LG · cs.AI
Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing approaches typically rely on large-scale supervised datasets, costly reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead. To address these challenges, we propose...
-
16
ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models
Kejing Wang, Toan Nguyen, Minh Hoang Nguyen, Simon Khan, Flora D. Salim
cs.LG · cs.RO
Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action policies. Although self-distillation can in principle provide denser training signals, we find that text-based privileged teachers conditioned on demonstrations, retrieved experiences, or high-level plans are ineffective for VLA adaptation, exposing a modality gap between...
-
17
Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning
Muhammed Furkan Dasdelen, Fatih Ozlugedik, Anastasia Litinetskaya, Nassir Navab, Carsten Marr, Ario Sadafi
cs.LG · cs.CV
Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities. We introduce a statistically grounded patient augmentation approach that generates realistic patients directly in embedding space. Using Gaussian Mixture Models as a probabilistic clustering approach on pooled instance embeddings from all patients, our method learns disease-specific "recipes"-statistical...
-
18
Deep Neural Networks with Ordinal Loss for Medical Applications
Tal Dvora, Rotem Haba, Gonen Singer
cs.LG
In many prediction problems in medical applications, target labels exhibit an inherent ordinal structure, where class ordering reflects clinically meaningful severity levels. The cost associated with misclassification is often non-uniform and asymmetric, as errors between distant ordinal categories may have substantially more severe consequences than errors between adjacent ones, and overestimating disease severity may have different clinical...
-
19
OncoSynth: Synthetic data generation for treatment effect estimation in oncology
Octavia-Andreea Ciora, Julian Welzel, Dennis Frauen, Maresa Schröder, Marie Brockschmidt, Harry Amad, Thomas...
cs.LG · cs.AI
In oncology, access to patient-level data is often restricted. Synthetic data provides an alternative for analyzing treatment effectiveness, but existing methods for synthetic data generation fail to preserve the causal relationships between covariates, treatments, and outcomes, thereby leading to biased estimates of treatment effects. Here, we introduce OncoSynth, a generative, causally-aware machine learning framework designed to produce...
-
20
Bridging Spherical Black-Box Optimizers
Johannes Ackermann, Stefano Peluchetti
cs.LG · math.OC
When gradient information is unavailable, black-box optimization (BBO) methods provide a practical alternative. While Evolution Strategies (ES), Consensus-Based Optimization (CBO), Optimization via Integration (OVI), and related methods have each been studied independently, their connections remain underexplored. We unify these approaches within a common theoretical framework, revealing that they differ primarily in two design choices:...
-
21
Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
Divake Kumar, Sina Tayebati, Devashri Naik, Amanda Sofie Rios, Nilesh Ahuja, Omesh Tickoo, Ranganath Krishnan, Amit...
cs.LG · cs.AI · cs.CL · cs.CV
Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severity ranking, and spatial safety regions. Yet evidence on post-hoc uncertainty quantification (UQ) for these agents is fragmented across isolated model and dataset pairs, leaving it unclear whether UQ rankings stay stable when the agent, benchmark, or observable...
-
22
Gradient-based inverse lithography for EUV masks via the waveguide method and a physics-informed neural operator
Vasiliy A. Es'kin, Egor V. Ivanov
cs.LG · cs.AI · math.OC · physics.comp-ph · physics.optics
Gradient-based inverse lithography technology~(ILT) for extreme ultraviolet~(EUV) masks is presented. A novel framework treats the differentiable waveguide method and the recently proposed waveguide neural operator~(WGNO) as end-to-end physics engines, recovering the permittivity of the absorber of the mask through automatic differentiation of the full forward diffraction model. Numerical experiments on realistic 2D and 3D absorbers of the...
-
23
Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
Yan Zhou
cs.LG
Foundation models are often used as fixed black-box predictors for downstream tasks with limited labeled data, but their predictions may be biased and unsafe to trust blindly. We study this setting through black-box assisted nonparametric regression: a learner observes labeled samples and can query a fixed predictor $f_0$, while the target $f^*$ is close to $f_0$ in $L_2(P_X)$ up to an unknown radius $δ$. We give a finite-sample minimax...
-
24
Cellular Predictions on the Move: What about Data?
Natalia Vesselinova, Pauliina Ilmonen
cs.LG · cs.NI
Mobile cellular load forecasting is native to network resource optimization and delivery of services with reliability, latency and quality guarantees. The mainstream of machine learning research in the area is focused primarily on developing powerful learning structures for improved prediction accuracy. The data used for forecasting traditionally belong to the cellular domain and at most contain exogenous information about the surroundings of...
-
25
Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning
Samuel Valland Lyngset, Tor Viljen Raanaas, Gard Sveipe, Eirik Møller Nilsen, Jim Torresen, Kai Olav Ellefsen, Tobias Lømo
cs.LG · cs.RO
When fine-tuning Large Language Models (LLMs), there has been success in minimizing both memory usage and computation with Parameter-Efficient Fine-Tuning (PEFT), like Low Rank Adaptation (LoRA). In this article, we have explored whether this approach is transferable to the world of robotics and Reinforcement Learning (RL), allowing learning with reduced memory usage and improved computational performance. Specifically, we focused on a...
-
26
Learning Subset-Shared Invariances for Domain Generalization with Mixture-of-Experts
Tien-Hung Nguyen, Tien-Dat Tran, M. -Duong Nguyen, Kok-Seng Wong
cs.LG
Domain generalization (DG) aims to learn a model from one or more source domains that generalizes to an unseen target domain without accessing target data during training. A common approach enforces invariance of representations across all source domains, assuming predictive structure is globally shared. However, we demonstrate that enforcing invariance across more domains gradually restricts the feasible representation space, discarding...
-
27
TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systems
Erdenebileg Batbaatar, Young Yoon
cs.LG · cs.AI · cs.CR · cs.DC
Distributed intelligent systems increasingly need to train across data silos without centralizing raw data. Federated learning keeps data local but can suffer under heterogeneous partitions and requires repeated full-model exchange. Split learning reduces communication through cut-layer activations, but standard protocols generally do not recover centralized mini-batch gradient behavior and may expose activations and gradients in plaintext....
-
28
Low-Complexity Policy Tessellations in Structured Markov Decision Processes
Fredy Pokou
cs.LG · cs.AI
We study optimal-policy geometry in structured Markov decision processes. While approximate dynamic programming and reinforcement learning typically approximate high-dimensional value functions, we show that optimal policies induce simpler decision tessellations. We propose boundary-based policy approximations that learn policy regions directly. A policy-loss decomposition links performance degradation to action margins and explains why...
-
29
Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks
Rupesh Raj Karn, Johann Knechtel, Ozgur Sinanoglu
cs.LG · cs.CR
As graph neural networks (GNNs) become standard tools for critical tasks in circuit design and analysis, their security and privacy risks require careful attention. Here, we present the first comprehensive evaluation of gradient leakage attacks (GLAs) on GNNs in circuit-design and hardware-security tasks, a practical threat that has been largely overlooked. We assess state-of-the-art (SOTA) GNNs, including GraphSAGE, GCN, GIN, and GAT,...
-
30
Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors
Guozheng Ma, Lu Li, Zilin Wang, Pierre-Luc Bacon, Dacheng Tao
cs.LG
Online reinforcement learning (RL) agents increasingly depend on knowledge acquired offline to achieve practical efficiency. Originally studied in offline-to-online RL, this paradigm now spans foundation model post-training and embodied intelligence, with prior types expanding from offline datasets and pre-trained policies to increasingly diverse knowledge sources such as multimodal foundation models and generative world models. Offline...
-
31
Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning
Bang Giang Le, Viet Cuong Ta
cs.LG · cs.MA
Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region framework of single-agent. Instead of relying on other agents' actions, the independent actors setting considers each agent to act based only on its local information, thus having more flexible applications. However, in the sequential update framework, it is required to re-estimate the joint...
-
32
Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning
Yifan Wu, Yiqi Wang, Xichen Ye, Wenjing Yan, Xiaoqiang Li, Cheng Jin, Xiangyu Yue, Weizhong Zhang
cs.LG
Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments. Yet the computational overhead of the distillation process itself is often overlooked, raising the question of whether a better student model can be obtained with less data and less compute via data pruning. However, existing data pruning methods are not designed for KD: some introduce substantial overhead, such as...
-
33
Towards Robust EEG Decoding Based on Riemannian Self-Attention
Shaocheng Jin, Tao Zhou, Rui Wang, Ziheng Chen, Xiaoqing Luo, Xiaojun Wu, Josef Kittler
cs.LG
Brain-Computer Interface (BCI) based on electroencephalography (EEG) enables direct interaction between the brain and external environments and has significant applications in assistive technologies, medical rehabilitation, and entertainment. Recently, EEG decoding methods based on Symmetric Positive Definite (SPD) learning have demonstrated superior performance. However, these methods typically employ basic network architectures and do not...
-
34
Learning with a Single Rollout via Monte Carlo Pass@k Critic
Fengdi Che, Yang Liu, Lei Yu, Meng Cao, Tong Che, Rupam Mahmood, Dale Schuurmans
cs.LG · cs.AI
Estimating token-level advantages in reinforcement learning (RL) for language models remains challenging because scaling up episodic experience collection is expensive. The difficulty intensifies for baseline advantage estimation methods, where repeated sampling causes trajectories to diverge into substantially different reasoning prefixes. In this context, RL algorithms such as GRPO prove limited: an outcome reward is too sparse to be...
-
35
The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms
Jinghan Zhang, Zerui Cheng, Shiqi Chen, Ge Zhang, Wenhao Huang, Jiashuo Liu, Junxian He, Tianle Cai
cs.LG · cs.CL
Traditional evaluations measure a learning algorithm's final performance on an i.i.d. test set, reducing learning to a single aggregate score. This approach obscures a fundamental question: to what extent does learning from a specific example generalize to others? Such per-sample generalization, akin to learning by analogy in human cognition, captures how far the knowledge extracted from one example can transfer, yet remains invisible to...
-
36
The Interplay of Harness Design and Post-Training in LLM Agents
Kyungmin Kim, Youngbin Choi, Seoyeon Lee, Suhyeon Jun, Dongwoo Kim, Sangdon Park
cs.LG · cs.CL
Tool-integrated LLM agents are often wrapped within a harness: the scaffolding that determines which tools are exposed, how they are described, and what auxiliary information accompanies each per-step observation. While agents are routinely post-trained, this scaffolding is typically treated as a fixed engineering detail, with design effort limited to the training-free regime. Moreover, existing post-training algorithms assume a static...
-
37
TopoCast: A Topological Fidelity Framework for Evaluating Transformer-Based Time Series Forecasting
Sandeepa Weerasekara, Sandareka Wickramanayake
cs.LG · cs.AI
Deep learning-based models have achieved state-of-the-art performance in Time Series Forecasting (TSF), yet their evaluation remains dominated by pointwise error metrics such as Mean Squared Error (MSE), which quantify numerical accuracy but overlook structural properties of the forecast signal, including recurrent dynamics, oscillatory behavior, and phase alignment. As a result, forecasts exhibiting over-smoothing, phase shifts, or frequency...
-
38
Interpretable Concept-Guided Polynomial Tabular Kolmogorov-Arnold Network for EEG-Based Mild Cognitive Impairment Detection
Yosef Bernardus Wirian, Qiang Cheng
cs.LG · cs.AI
Early and scalable detection of mild cognitive impairment (MCI) remains an unresolved clinical challenge. Existing EEG-based screening approaches are constrained by handcrafted feature pipelines that discard neurophysiologically meaningful domain structure and deep learning classifiers that sacrifice interpretability for performance. No existing work unifies physiologically organized concept encoders, cross-concept interaction modeling, and...
-
39
Brevity is the Soul of Inference Efficiency: Inducing Concision in VLMs via Data Curation
DatologyAI, :, Matthew L. Leavitt, Siddharth Joshi, Haoli Yin, Rishabh Adiga, Haakon Mongstad, Alvin Deng, David...
cs.LG · cs.AI · cs.CV
Inference efficiency is typically pursued by shrinking the model: distillation, pruning, quantization, and sparse routing each lower per-token cost while treating token count as fixed. But output length has been inflating, and it is precisely the component the standard toolkit leaves untouched. Here, we argue that brevity is the missing inference-efficiency lever, and that pretraining data curation is a practical way to pull it: a model...
-
40
DFMU: Data-Frugal Machine Unlearning
Sajith U, Prateek Keserwani
cs.LG
Machine unlearning is an emerging domain that ensures the safe removal of elements (includes concepts, attributes, entity and class) from the trained model along with least drop in model performance. The domain of machine unlearning brings its own indigenous challenges since the removal of pre-trained elements from model will always degrade the model performance on remaining elements. The existing methods basically rely on retraining for...
-
41
FactorLibrary: From Polynomials to Circuits via Recursive Subgoals
Rohan Pandey, Michael Ruofan Zeng, Weikun K. Zhang, Kaijie Jin, Naomi Morato, Archit Ganapule, Bhaumik Mehta, Jarod Alper
cs.LG · cs.AI
Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory. We formulate it as a reinforcement learning problem in two directions, bottom-up and top-down. To address the challenge of a fast-growing combinatorial search space, we introduce FactorLibrary, which stores factorizable subexpressions that serve as reusable subgoals across training episodes. We...
-
42
Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
Yivan Zhang, Ziyan Luo, Manuel Baltieri
cs.LG · cs.AI · math.CT
State abstraction plays a key role in scaling reinforcement learning to complex but structured systems. In studying such systems, a wide range of behavioral structures have been studied in reinforcement learning, including value functions, invariants, bisimulation relations, and behavioral metrics. However, a general principle for determining what structures are provably preserved under state abstraction is still lacking. In this paper, we...
-
43
Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning
Hongye Xu, Bartosz Krawczyk
cs.LG · cs.CV
Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space. While maintaining class-conditional Gaussian statistics provides a principled classification strategy, these parametric summaries remain sensitive to anisotropic representation drift. Existing methods often transport these statistics across tasks using a decoupled, post-hoc paradigm: optimizing a backbone without explicit...
-
44
Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention
Luke McDermott, Robert W. Heath, Rahul Parhi
cs.LG
Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context learning. The quadratic nature of attention, however, prohibits transformers from performing this process on arbitrarily long sequences. In this work, we argue that extending in-context learning to lifelong settings is a practical solution for continual learning in AI agents. In particular, we...
-
45
Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods
Zhengzhu Liu, Zeming Gao, Haoyuan Qin, Jiawei Hu, Junhao Wu, Miao Zhu, Haipeng Zhang, Chennan Ma, Siqi Shen, Cheng Wang
cs.LG
Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring to new task instances. We trace this issue to stagnant neurons, units whose gradient updates become negligibly small relative to their weights, thereby hindering learning. While existing plasticity injection methods exist, they prove ineffective for such neurons. To address this, we propose...
-
46
Communicability-Inspired Positional Encoding (CIPE)
Yipeng Zhang, Zhongtian Sun, Pietro Liò, Kelin Xia
cs.LG · cs.AI
Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging. Such encodings should ideally induce an Attention-Compatible Geometry for self-attention: not merely describing graph structure, but defining a geometry whose inner products reflect meaningful structural relatedness. To realize this geometry, we propose Communicability-Inspired Positional Encoding (CIPE), built...
-
47
EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression
Ke Xu, Jiaqi Wan, Wenhao Hu, Han Pu, Xiaoyun Wang
cs.LG · cs.AI
Post-Training Sparsity (PTS) has emerged as a crucial paradigm for compressing Large Language Models to facilitate efficient deployment on resource-constrained devices. However, existing PTS methodologies are typically confined to Single-Sparsity optimization, necessitating a separate, time-consuming optimization session for each specific sparsity level. This rigid paradigm significantly hinders flexible deployment across diverse hardware...
-
48
UC-Search: Risk-Aware Test-Time Search for Delayed Constrained Time-Series Control
Xibai Wang
cs.LG · cs.AI
Time-series models are usually scored as forecasters, yet deployed systems often require delayed decisions under uncertainty and hard feasibility constraints. UC-Search is a model-agnostic test-time wrapper: a backbone emits forecasts or action scores, a feasibility automaton rolls candidate paths forward, and bounded search returns the first action of a risk-adjusted feasible trajectory. We instantiate UC-Beam and a UCT-style UC-MCTS...
-
49
Inverse Reinforcement Learning for Interpretable Keystroke Biomarkers in Parkinson's Disease
Navin Bondade
cs.LG
Keystroke dynamics have been explored extensively as a passive digital biomarker for Parkinson's disease (PD), typically by extracting summary statistics from typing timing and training a classifier to discriminate PD from healthy controls. We instead apply inverse reinforcement learning (IRL) to keystroke data, modeling each keystroke as a discrete choice over typing speed and recovering, per subject, an interpretable reward function that...
-
50
Variational Inference via Entropic Transport Descent
Vincent Pacelli, Akash Ratheesh, Evangelos Theodorou
cs.LG
Particle-based variational inference (ParVI) methods approximate an intractable target distribution by evolving an ensemble of interacting samples. Existing approaches rely predominantly on kernel-based repulsion (e.g., SVGD), which suffers from variance collapse in high dimensions and mode collapse on multimodal targets -- pathologies caused by the absence of global transport structure. We introduce entropic transport descent (ETD), a ParVI...
-
51
Semantic Allocation in Ordered Bottlenecks: Predictive Residual Inference for Visual Representation Learning
Erik Ayari, Manuel Traub, Martin V. Butz
cs.LG · cs.CV
Ordered bottlenecks aim to provide utility at flexible budgets by assigning coarse information to early tokens and task-relevant detail to later ones. Prior work, including tail dropping (TD), typically enforces ordering by means of a masking-based ordering pressure (MBOP): Late tokens are masked more frequently than early tokens and are therefore encouraged to store less essential fine details. We introduce predictive residual inference for...
-
52
ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments
Taicheng Guo, Haomin Zhuang, Kehan Guo, Yujun Zhou, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang
cs.LG · cs.AI · cs.CL
Hyperparameter Optimization (HPO) is essential for maximizing machine learning model performance, and its core challenge is sample efficiency: finding strong configurations within a limited budget. Because every HPO tool relies on a surrogate prior that imparts its own inductive bias, individual tools struggle once problems become sufficiently diverse and drift from these priors. Motivated by the reasoning and generalization capabilities of...
-
53
FDN: Interpretable Spatiotemporal Forecasting with Future Decomposition Networks
Nicholas Majeske, Ariful Azad
cs.LG · cs.AI
Spatiotemporal systems comprise a collection of spatially distributed yet interdependent entities each generating unique dynamic signals. Highly sophisticated methods have been proposed in recent years delivering state-of-the-art (SOTA) forecasts but few have focused on interpretability. To address this, we propose the Future Decomposition Network (FDN), a novel forecast model capable of (a) providing interpretable predictions through...
-
54
A Hybrid CNN-LSTM Intrusion Detection Framework for Cybersecurity in Smart Renewable Energy Grids
Sajib Debnath, Remon Das
cs.LG · cs.AI
The accelerated digitalization of renewable energy smart grids through IoT sensors, AMI, and SCADA systems has significantly expanded the attack surface for sophisticated cyberattacks, FDI attacks that stealthily distort state estimation and DoS/DDoS attacks that flood communication channels. Current IDS, however, exhibit three inherent limitations: inadequate modeling of the temporal progression of multi-step attacks, degraded scalability...
-
55
Efficient Adaptive Data Acquisition via Pretrained Belief Representations
Daolang Huang, Zhuoyue Huang, Conor Hassan, Luigi Acerbi, Samuel Kaski, Tom Rainforth
cs.LG · stat.ML
Learning effective policies for adaptive data acquisition remains challenging: posterior-based methods rely on surrogate models and posterior approximations that can be misspecified or biased, while direct policy-learning methods map from historical observations and fail to exploit available model representations, making learning harder. We introduce policy learning with belief representations (POLAR), based on the insight that optimal data...
-
56
Efficient Analytic Uncertainty Quantification for Multi-Modal Regression
Kun Jin, James Harrison, Jiawei Li, Sihan Liu, Jiayi Liu, Randolph Linderman, Yuening Li, Arnab Bhadury, Sourabh...
cs.LG
Efficient uncertainty quantification (UQ) is essential for trustworthy large-scale learning. Existing UQ methods for regression tasks mainly operate under the assumption that the conditional label marginal satisfies single-peak parametric models, e.g., Gaussians, where the negative log-likelihood function simplifies to the mean square error. However, such single-peak assumptions fail in regression tasks featuring multi-modal distributions. On...
-
57
Neural operator-based digital twins for modeling amyloid-$β$ and tau propagation and treatment optimization in Alzheimer's disease
Xiaofeng Xu, Tingting Dan, Zifan Zhou, Bin Li, Guorong Wu, Wenrui Hao
cs.LG · math-ph
Accurately predicting the spatiotemporal evolution of amyloid-$β$ and tau proteins at the individual level is critical for improving the diagnosis and treatment of Alzheimer's disease. We consider the problem of constructing patient-specific digital twins that model the propagation of these biomarkers on the cortical surface using reaction--diffusion dynamics. A major challenge is that the underlying nonlinear aggregation mechanisms are...
-
58
EveLoad: Cognitive Workload Recognition from Event-Based Eye Movements
Guorui Lu, Shaohua Guan, Zhen Xu, Qinyu Chen
cs.LG · cs.HC
Cognitive workload monitoring is important for adaptive rehabilitation and assistive interfaces, where task difficulty, pacing, and feedback should be adjusted according to the user's cognitive state to avoid overload and under-challenge. Emerging extended reality and robot-assisted rehabilitation environments provide controllable training tasks, but they require unobtrusive sensing methods that can capture rapid ocular dynamics during...
-
59
An iterative energy-based multimodal transformer for joint retrieval of wheat soil moisture, leaf area index, and plant height from Sentinel-1 and Sentinel-2 time series
Shubham Kumar Singh, Peilei Fan, Suraj A. Yadav, Rajendra Prasad, Prashant K Srivastava
cs.LG · cs.CV · eess.IV
Field-scale retrieval of surface soil moisture (SM), leaf area index (LAI), and plant height (PH) is essential for precision agriculture, yet it remains an ill-posed inverse problem. Concurrent variations in soil moisture and canopy density generate substantial ambiguities in radar backscatter and spectral responses, which reduces the effectiveness of traditional feedforward regression models in heterogeneous smallholder cropping systems....
-
60
The Gentle Collapse: Distributional Metrics for Continual Learning
Ahmed Anwar, Andreas Wagner, Federico Raue, Tobias Nauen, Andreas Dengel
cs.LG
Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapses discretely at task boundaries, hiding the internal structure of what is being forgotten. We introduce six softmax-derived metrics spanning true-label rank (TLR), predictive confidence, and distributional divergence that characterize forgetting continuously, each...
-
61
ATMA: Length-Invariant Language Modeling via Polar Attention and Gated-Delta Compression Memory
Habibullah Akbar
cs.LG · cs.AI
Modern large language models based on softmax scaled-dot-product attention are constrained by their training sequence length: as the key-value sequence grows, softmax probability mass can dilute across a wider distribution, inducing activation shift and long-context performance collapse. Moreover, long-context language modeling faces a structural tension: a sliding-window attention core maintains a bounded local representation and low...
-
62
Silent Failures in Physics-Informed Neural Networks: Parameter Poisoning and the Limits of Loss-Based Validation
David McShannon, Nicholas Dietrich
cs.LG · cs.AI
Physics-informed neural networks (PINNs) embed governing equations in their loss function, enabling mesh-free solutions to partial differential equations. Low training loss is treated as evidence that the learned solution is physically correct. This paper shows that assumption breaks down when encoded physics are incorrect. By perturbing PDE parameters before training, a setting we describe as physics parameter poisoning or parameter...
-
63
Reward-Conditioned Attention: How Reward Design Shapes What Autonomous Driving Agents See
Mohamed Benabdelouahad, Ahmed Djalal Hacini, Nadir Farhi, Aissa Boulmerka
cs.LG · cs.AI · math.OC
We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving. Using three Perceiver-based agents that share identical architectures and training data but differ only in their reward configurations$\unicode{x2014}$ranging from basic violation penalties to continuous proximity penalties$\unicode{x2014}$we analyze cross-attention allocation across 50 real-world scenarios...
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.