cs.LG · 2026-08-04 · No. 74
Machine Learning, 2026-08-04.
51 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
51 entries-
01
onepot-Bench 0: towards lab-aware in silico chemistry benchmarks
Brandon Wang, Andrei S. Tyrin, Daniil A. Boiko
cs.LG
Language models are playing an increasingly important role in laboratory science, performing tasks such as experiment planning, execution, and post-hoc analysis. However, precisely measuring their abilities is difficult, as scientific capabilities require a mixture of both problem-solving skills and domain-specific intuition. Existing evaluations rarely measure the capabilities required to make reliable decisions in a physical laboratory and...
-
02
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Zhaoxin Yu, Qi Shen, Hengli Li, Zhaowei Zhang, Song-Chun Zhu, Chi Zhang, Zilong Zheng
cs.LG · cs.CL
Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping model parameters frozen. Existing methods, however, typically connect these states to the reasoning trajectory through decoded tokens, making sequence-level credit assignment indirect and obscuring how latent updates shape subsequent reasoning. We introduce GradCuit (gradient through circuit),...
-
03
Smooth Reparameterizations of Functions on Simplicial Product Spaces: Applications to Probabilistic Tensor Decomposition and Functional Data Registration
Shashwat Kumar, Arafat Rahman, Anuj Srivastava, P. -A. Absil
cs.LG
We consider optimization problems defined on product spaces of simplices. Examples of this class of problems include learning low-rank discrete multivariate probability distributions via simplex constrained tensor decomposition and performing functional data registration under the Square Root Velocity Function (SRVF) representation. In this work, we demonstrate the feasibility of replacing the product simplex with a smooth, elementwise...
-
04
Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality
Shengzhi Deng, Chenqi Ye, Yanze Guo
cs.LG · stat.ML
Diffusion models rely on stochastic inputs, yet on finite-precision hardware, the "randomness" they consume is realized as deterministic numerical orbits generated by pseudorandom rules. Accessible orbit structure can become a learnable input and affect both training and generation because the realized loss and its gradient depend on the concrete pseudorandom values consumed at each optimization step. A small multilayer perceptron predicts...
-
05
Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection
Anusha Madan Gopal, Aras Pirbadian, Kristofor D. Carlson, M Anthony Lewis, Jonathan Tapson
cs.LG · cs.AI · cs.IR
Retrieval-augmented generation (RAG) imposes a prefill cost proportional to retrieved context length, and -- with Transformer backbones -- a KV-cache that grows with each generated token. State-Space Models (SSMs) avoid the second cost by construction; we eliminate the first, collapsing prefill from $O(L_{context})$ to $O(1)$ per query. We introduce PRECOG (Pre-Computed Context Injection), a retrieval mechanism that exploits a property unique...
-
06
Benchmarking Sheaf Neural Networks for Inductive Tasks
Stefano Fiorini, Edoardo Coppola, Pietro Liò
cs.LG
Sheaf Neural Networks (SNNs) generalize message passing by replacing scalar edge weights of standard Graph Neural Networks (GNNs) with learnable, edge-dependent restriction maps between node stalks. Despite their strong theoretical foundations and promising transductive results, SNNs have been evaluated almost exclusively on transductive node classification, leaving their behaviour under inductive protocols unknown. We address this gap...
-
07
Uncertainty Is Not Enough: Value-of-Information Routing for Mixtures of LoRA Experts
Tom Saliencro, Rohan Desai, Priya Nair, Maya Lindqvist, Daniel Whitmore
cs.LG
Mixtures of low-rank adaptation experts increase parameter-efficient capacity by routing each input through a subset of adapters. Recent dynamic routers activate more experts when the router or prediction is uncertain. This rule silently equates uncertainty with useful additional computation: an uncertain example may contain complementary, unqueried expert evidence, but it may instead remain ambiguous after every expert agrees. We formulate...
-
08
Analytic Planning under Uncertainty with Moment Closure
Shishir Sharma, Doina Precup
cs.LG · cs.AI
Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty. Propagating full state distributions analytically offers a principled way to do this, but has traditionally required restrictive policy or reward structures to remain tractable. Consequently, modern deep reinforcement learning has largely retreated to either stochastic sampling, which introduces significant...
-
09
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
Yi Yang, Zhennan Chen, Yihong Zhuang, Tiehan Fan, Yinan Chen, Jian Li, Jian Yang, Ying Tai
cs.LG · cs.CL
Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges. First, trajectory-indexed utilities grow with the interaction history, thereby dispersing limited feedback over an ever-expanding state space. Second, because trajectory-level rewards are jointly assigned to co-retrieved memories, irrelevant experiences may receive misleading utility updates and consequently enter the memory-reward trap. To address...
-
10
Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees
Zejun Xie, Xintong Li, Guang Wang, Desheng Zhang
cs.LG · stat.ML
Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground truth. Existing approaches face a dilemma: methods using only human judgments suffer from heterogeneous expertise and inconsistent rating scales, while methods using only model-generated scores must learn from imperfect proxies or incomplete features. We propose Aggregate-then-Calibrate...
-
11
Foundations of Reinforcement Learning and Control:Connections and New Perspectives
Claire Vernade, Onno Eberhard, Martha White, Florian Dörfler, Csaba Szepesvári, Miroslav Krstic, Michael Muehlebach
cs.LG
Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback. While both fields have common roots in dynamic programming, they have evolved with distinct methodologies, goals, and cultures. Despite decades of mutual influence, a significant gap persists between the two communities. This tutorial introduces adaptive control, actor-critic...
-
12
Why Large Language Models Fail at Tabular Prediction
Marta Garnelo, Wojciech M. Czarnecki
cs.LG
Large language models (LLMs) have become the default tool for a remarkable range of tasks, yet they have had conspicuously little success at one of the most common machine learning workloads: predictive analytics over tabular data. This gap is the founding premise of the fast-growing field of tabular foundation models, but the question of why generic LLMs fail has remained open. We study a frontier LLM in its purest inference regime - a...
-
13
Deep Learning-Based Estimation of Ground Reaction Forces in Parkinsonian Gait Using an Optimized Set of IMU Data
Run Lin, Yingtian Tang, Jiawen Xu, Dongfei Huo, Lefan Wang, Helen Dawes, Dominic J. Farris, Dong Wang, Xijin Hua
cs.LG · eess.SP
Accurate gait analysis in Parkinson's disease (PD) typically relies on laboratory-based systems to capture biomechanical data, such as ground reaction forces (GRFs). Estimating GRFs using inertial measurement units (IMUs) provides a feasible alternative. However, this approach remains challenging in pathological gait like PD due to its high variability and complexity. Moreover, existing monitoring approaches often require multiple...
-
14
From fragmented data to actionable design: Physics-calibrated learning for plastic upcycling
Jingyang Bai, Zijia Wang, Xiangyi Long, Marcos Millan, Binjian Nie, Mingyue Ding
cs.LG · cs.AI
Thermochemical upgrading of plastic waste is a key upcycling pathway, yet the experimental literature is fragmented by heterogeneous conditions and incomplete reporting. Complete-case learning would retain only 10.99% of the curated experiments, while target imputation can introduce biased supervision. Here we develop a Physics-Calibrated, Missingness-Gated, and Load-Balanced Mixture-of-Experts (PC-MG-MoE) framework that converts structured...
-
15
Gecko: Fast Private Inference via Secure Public Encoder Offloading
Cheng'an Wei, Kai Chen, Yue Zhao, Congyi Li, Shenchen Zhu
cs.LG
Private inference protects both user inputs and server models during neural network inference, but existing solutions remain too slow for practical deployment. This motivates recent efforts to run a public encoder, such as a pretrained backbone, outside the protection boundary and evaluate only a small private predictor cryptographically. While appealing for efficiency, this design is not inherently secure: naively offloading a public encoder...
-
16
GLAIM: Learning Global and Local Adaptive Inter-Variable Dependency for Multivariate Time Series Imputation
Mingyang Wang, Rongwen Li, Xiao Wang, Changjian Chen
cs.LG · cs.AI
Multivariate time series imputation is fundamental to downstream analysis, yet modeling inter-variable dependencies with incomplete observations remains challenging. Existing methods learn global dependencies across samples or dynamic local dependencies per sample. Global dependencies are stable but adapt poorly to sample variations and temporal non-stationarity, whereas local dependencies are adaptive yet unreliable when observations are...
-
17
Qwen-CUA: Native Computer Use for (almost) Everything
Dunjie Lu, Shuai Bai, Tianyi Bai, Sicheng Fan, Chang Gao, Jian Guan, Feng Hu, Mianqiu Huang, Xingyang Huang, Yizhen...
cs.LG · cs.CL
Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone. It observes only screenshots and acts through keyboard and mouse events, without DOM trees, accessibility...
-
18
Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning
Botao Dong, Longyang Huang, Ning Pang, Hongtian Chen
cs.LG · cs.AI · eess.SY
In offline reinforcement learning (RL), the distribution shift between behavioral data and the learned policy can lead to erroneous \emph{Q}-value estimation, thereby misguiding the direction of policy optimization. To address this issue, we develop a behavioral advantage corrected policy evaluation (BAC-PE) approach, which utilizes the \emph{Q}-function of the behavior policy to correct the learned policy's \emph{Q}-function, thus mitigating...
-
19
BRiG-AFA: Bellman Risk-to-Go Learning for Non-Myopic Active Feature Acquisition
Jiaorong Feng, Qian Li, Ying Li
cs.LG · cs.AI
Active feature acquisition (AFA) asks which unobserved feature to measure next for each test instance under a budget. Greedy rules are easy to train but can overlook context features whose value is realized only through later acquisitions, while reinforcement-learning and generative approaches introduce difficult optimization or conditional-density estimation. We introduce \method, a deployable, supervised alternative that learns a separate...
-
20
Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures
Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni, Andrea Cossu, Davide Bacciu, Antonio Carta
cs.LG
Parameter-Efficient Fine-tuned (PEFT) models are frequently downloaded from open repositories by practitioners. This widespread practice creates a significant attack surface, as malicious actors can publish backdoored models that induce specific behaviors in response to predefined triggers. We study the problem of weight-space backdoor detection, where a detector classifier predicts whether a model is malicious using only its weights,...
-
21
Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning
Yuan-Heng Tsai, Li-Hsing Yen, Yan-Wei Chen
cs.LG · cs.AI
Federated learning (FL) is a popular distributed learning framework where multiple clients perform local training and a server aggregates the locally updated models. FL enables decentralized training while preserving the privacy of clients' datasets. However, non-independent and identically distributed (non-IID) or noisy datasets can lead to low model accuracy or high convergence latency. Precluding these clients through client selection may...
-
22
Constrained Co-Design for Photonic Bayesian Neural Networks
Hendrik Borras, Xiao Wang, Bernhard Klein, Robin Janssen, Frank Brückerhoff-Plückelmann, Wolfram Pernice, Holger Fröning
cs.LG
Classical neural networks frequently produce overconfident predictions on ambiguous or out-of-distribution (OOD) data, a liability that grows with each AI system deployed in safety-critical real-world scenarios. Bayesian neural networks (BNNs) provide a principled framework for uncertainty-aware prediction by replacing deterministic parameters with probability distributions, but repeated sampling increases latency, memory traffic, and energy...
-
23
CRIP: Channel Level Representation Injection for Personalized One-Shot Federated Learning
Zijian Jiang, Chaoli Sun, Handing Wang, Xilu Wang
cs.LG
One-shot federated learning (OSFL) has emerged as a promising collaborative model learning framework with only a single round of communication, offering significant advantages in communication efficiency and privacy preservation. However, OSFL often faces inherent limitations under severe domain heterogeneity across clients due to the lack of iterative knowledge exchange. Most existing OSFL methods require an auxiliary public dataset for...
-
24
Start Classifying: Categorical Critics for LLM Reinforcement Learning
Zhijian Zhou, Long Li, Xuan Zhang, Zongkai Liu, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi
cs.LG
Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets. Although scalar MSE is statistically valid for estimating the conditional expected return, sparse binary rewards in reinforcement learning with verifiable rewards (RLVR) make critic optimization and calibration especially consequential: small value errors directly distort the scalar...
-
25
Empowering Credit Risk Detection in Weixin Pay with Billion-Scale Deep Graph Learning
Xin Liu, Xiyuan Chen, Chenglong Wu, Xuan Zong, Jun Zhou, Dawei Cheng
cs.LG
Credit risk detection, particularly mitigating individual fraud, is crucial for maintaining the stability of digital financial ecosystems. Accurately identifying credit fraud among billions of users is critical for minimizing financial losses and safeguarding the sustainability of inclusive financial services. Given that credit fraud risks are often concealed within heterogeneous user-risk graphs, Graph Neural Networks (GNNs) have emerged as...
-
26
RamanPFN: learning from Raman spectral structure with a tabular foundation model
Xingyu Pan, Huan Wang, Jinjia Guo, Zhenlin Zhao, Siming Dong, Jixi Lu
cs.LG · cs.AI
Raman spectroscopy enables non-destructive, label-free molecular characterization across materials science, biomedicine and process monitoring. Predictive Raman datasets often contain few labelled spectra and thousands of ordered wavenumbers, with informative variation within bands and across distant spectral regions. Latent-variable chemometrics accommodates collinear small-sample data but can obscure fine peak morphology, whereas deep...
-
27
CoRe-GNN: Multilevel Message passing on Coarsened graphs
Antonin Joly, Nicolas Keriven, Aline Roumy
cs.LG
Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers. We show that several existing scalable approaches can be written as structured modifications of the GNN propagation matrix, providing a unified perspective that exposes their respective limitations. In particular, graph coarsening replaces it by a low-rank approximation that enables spectral guarantees but assigns...
-
28
Do Static Embeddings Add Value to Hybrid Dutch Retrieval?
António Pereira Barata
cs.LG · cs.IR
Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking information once lexical and transformer-based retrieval are already combined. We present a controlled evaluation of this question across Dutch retrieval tasks from the Massive Text Embedding Benchmark for Dutch (MTEB-NL). Weighted reciprocal rank fusion (RRF) combines Best Matching 25 (BM25),...
-
29
One QK Channel, Many Sources: Guarding Low-Precision Attention Collapse
Shuxiao Xie, Shuyang Xie, Yuan Cao, Dezhi Ran, Wei Yang, Tao Xie
cs.LG
A bfloat16 transformer can train normally for many steps and then collapse abruptly. Distinct low-precision errors can trigger the same failure, leaving unclear whether each source needs its own repair or one shared route can be blocked. We isolate a reproduced GPT-2-class collapse to the streaming-softmax accumulator, where fp32 accumulation repairs it, and use the fault as an assay for moving controlled errors across sources. Errors placed...
-
30
How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models
Andres Algaba, Francesca Carlon, Lynn Delcon, Marthe Ballon, Bert Verbruggen, Vincent Ginis
cs.LG · cs.AI
Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden. We introduce an observability ladder that holds each completed run fixed and varies only what a reader inspects to judge whether the answer is correct: the response, a self-summary the model writes from the trace, the trace itself, and internal signals, each with and without the prompt. Across three benchmarks and...
-
31
An AI-Based Decision-Support Pipeline for Day-Ahead Photovoltaic Forecasting
Fariba Dehghan, Sebastian Stein, Vahid Yazdanpanah, Stephanie Gauthier, Masood Nazari
cs.LG · cs.AI · eess.SY
Reliable photovoltaic (PV) forecasts are needed for low-carbon energy systems, but newly deployed sites often have short, imperfect records. This makes standard day-ahead forecasting difficult: persistence and physical baselines can be sensitive to calibration and timestamp alignment, while single machine-learning models may capture only one structure in the data and overstate skill under non-temporal validation. We study this problem at a...
-
32
A 2-Block Architecture for Real-Time EEG Gait Decoding: A Pilot Study
Shantanu Sarkar, Saurabh Prasad, Jose L. Contreras-Vidal
cs.LG · cs.HC · eess.SP
Closed-loop lower-limb exoskeleton control via Electroencephalography (EEG) remains limited by motion artifacts, low signal-to-noise ratio, and binary gait formulations that fail to capture full cortical gait complexity. We propose a 2-block Brain-Computer Interface (BCI) architecture: a trainable session-specific Feature Extraction Block with real-time artifact suppression and multi-domain feature extraction, coupled with a Decoder Block...
-
33
Isotonic Bradley-Terry Model for Paired Comparison Data
Ryoya Yamasaki
cs.LG
In this paper, we study prediction problems for paired comparison data, for example, predicting the win probability between two unmatched players and ranking all the players according to the order of their strengths by using win probability data between two matched players. Paired comparison data are typically analyzed using Bradley-Terry and Thurstone-Mosteller models. These models predict the win probability by transforming the difference...
-
34
Feed-Forward Steering in Transformer Residual Dynamics
Timur Mudarisov, Mikhail Burtsev, Radu State
cs.LG · math.DS
Attention-only dynamical theories model Transformer residual directions as particles aggregating on a sphere. We extend this framework by incorporating the feed-forward network (FFN) term as a local steering field acting on each token state. The resulting theory predicts that the tangential component of the FFN field is necessary for motion in residual-direction space, that critical residual directions correspond to nonlinear projective...
-
35
Geometry-Guided Layerwise FFN Width Allocation in Transformers
Timur Mudarisov, Mikhail Burtsev, Radu State
cs.LG · cs.AI · cs.CL
Feed-forward networks (FFNs) account for a large fraction of Transformer parameters, yet their hidden width is usually constant across depth. We ask whether this capacity can instead be allocated from a forward-pass measurement of layer behavior. We view each FFN as transporting a cloud of token representations and quantify the induced geometric change using correspondence-preserving shift, Gromov-Wasserstein distortion, and degree-one...
-
36
SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning
Junhao Cai, Dohun Kim, Sung Il Choi, Juhyun Park, Chengjun Jin, Dowon Kim, Changhee Joo
cs.LG
Source-free class unlearning erases whole classes using only the forget data, judged at the representation level, where features can leak a class the head no longer predicts. Existing feature-space erasers answer with one fixed projection, yet forget and retain classes share a representation, so deleting one disturbs the other where they overlap. We prove this tension is a frontier. Every fixed projection that deletes pays a retain cost of at...
-
37
Secrets Everywhere: Auditing Memorization in Mobility Prediction Models
Anne Josiane Kouam, Hristo Boyadzhiev, Konrad Rieck
cs.LG
Human mobility prediction models, which forecast the next location in a user's trajectory, are increasingly deployed in urban analytics, navigation, and personalized services. Yet, little is known about their potential to memorize and expose sensitive user trajectories from training data. While memorization has been extensively studied in language models, mobility prediction poses unique challenges: training sequences encode human behavior at...
-
38
Convex Neural Energy Elements: Monolithic Finite-Element Assembly of Geometry-Parameterized Neural Operators with Stability and Error Guarantees
Hongyue Jiang, Jianjiang Zhan, Chenzhuo Zhang, Fan Wang
cs.LG
Extending the neural-operator element method from individually trained, fixed-geometry neural elements to a library of reusable, geometry-parameterized element types fails structurally: a field-predicting operator trained by value regression induces an energy whose assembled Hessian is indefinite, and Newton converges to spurious minima (247% error) even with 1%-accurate field predictions. We introduce convex neural energy elements: each...
-
39
Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement Learning
Abdelghani Ghanem, Mounir Ghogho
cs.LG
Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logged actions that follow it, inducing a pessimistic bias that grows with the horizon. We propose Expectile $n$-step Q-learning (ENQ), which replaces the symmetric $n$-step temporal-difference (TD) loss with an asymmetric expectile loss on the action-value error, with expectile level $τ$ as the...
-
40
DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling
Yixiao Qian, Song Chen, Pengkai Wang, Jiaxu Liu, Shengze Cai, Chao Xu
cs.LG
Modern language models are built primarily from Transformers, recurrent models, and their hybrid architectures. Transformers rely on token-level attention memories, while recurrent models such as state space models (SSMs) and linear attention maintain compact recurrent states. These architectures are typically instantiated separately or interleaved at the layer level, leaving open whether a shared memory representation can support both...
-
41
Scikit-fingerprints: Python library for scikit-learn compatible molecular fingerprints and chemoinformatics
Jakub Adamczyk, Adam Staniszewski
cs.LG · cs.SE
We present scikit-fingerprints, a comprehensive, fully scikit-learn compatible library for molecular machine learning in Python, based on RDKit. Molecular fingerprints and related functionalities are workhorses of chemoinformatics, yet the widely used open-source frameworks are not compatible with the wider Python machine learning ecosystem based on scikit-learn conventions. scikit-fingerprints closes this gap, bringing molecular...
-
42
AOS: Adaptive Optimizer Switching via Training-State Signals for Faster Convergence and Better Generalization
Alok Kumar Pandey, Umang Chaturvedi, Aatish Rana, Gopi Krishna Nedanuri
cs.LG
Single-optimizer training is a poor fit for the distinct phases of deep network optimization: adaptive methods handle noisy early gradients well but overshoot flat minima, while SGD with momentum generalizes better in the late phase but converges slowly early on. We introduce AOS-R (Adaptive Optimizer Switching, Rule-Based), a lightweight controller that monitors six online gradient-space signals -- gradient noise scale (GNS), Hutchinson...
-
43
ChaosProbe: A Neurochaotic Lens on Frozen Transformer Input-Embedding Spaces
Kunal Kumar Pant, Nithin Nagaraj
cs.LG · cs.NE
Transformer models are most often understood through what they do: their benchmark performance, generation quality, or behavior on downstream tasks. Yet frozen transformer input-embedding spaces may also be examined through their responses to a controlled deterministic probe before contextual computation or task-specific adaptation. Guided by this response-based view, we introduce \emph{ChaosProbe}, a deterministic neurochaos-inspired method...
-
44
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
Luan Zhang, Ruochen Zhou, Dandan Song, Zhengyu Chen, Yuhang Tian, Jun Yang, Huipeng Ma, Chenhao Li, Guangyuan Feng,...
cs.LG · cs.CL
Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments. Recent work has proposed automatic harness evolution, which iteratively improves the harness from agent--environment interactions. However, existing methods often overfit to the evolution tasks, rely exclusively on trajectory-derived signals, and optimize harness components...
-
45
Finite-Time Analysis of Discounted Exponential-Utility Reinforcement Learning
Ankur Naskar, Vivek T A, Aditya Kumar, Gugan Thoppe, Prashanth L. A
cs.LG
Discounted exponential utility provides a principled criterion for risk-sensitive sequential decision-making, but its nonlinear structure complicates reinforcement learning. A recent work \citep{thoppe2026reinforcement} addressed this difficulty by introducing a Bellman-compatible surrogate and two model-free fixed-point algorithms for optimizing it over stationary policies. However, their main convergence results are asymptotic. In this...
-
46
Understanding and Correcting Low-Frequency Bias in EEG Foundation Model
Junjie Yu, Zihan Deng, Jianyu Zhang, Junrong Mu, Jiahui An, Wenxiao Ma, Ziling Lu, Yue Wang, Yan Zhu, Kexin Lou, Quanying Liu
cs.LG
Increasing EEG pretraining data scale or model capacity does not consistently improve downstream performance. We identify a persistent low-frequency bias in representations learned by diverse EEG foundation models, which remains across dataset scales, model capacities, and pretraining objectives. Our analysis links this bias to the interaction between EEG's $1/f^α$-like spectral structure and neural networks' tendency to preferentially learn...
-
47
CARE: A Cascaded Framework for Efficient and Reliable Time Series Anomaly Detection
Zemin Chao, Qianhui Xu, Jianhe Cen, Guangzhi Ge, Xiao Chen, Hoangzhi Wang
cs.LG
While deep learning models have achieved state-of-the-art performance in time series anomaly detection, their complex architectures incur substantial inference overhead. Existing methods typically apply a uniform inference strategy across all data points, which is inefficient given that anomalies are inherently scarce and the vast majority of temporal data consists of predictable normal patterns. To mitigate this bottleneck, we propose CARE,...
-
48
LAB-Tab: LLM-Augmented Bayesian Network Adaptation for Few-Shot Tabular Generation
Zijian Shen, Taijie Chen, Bin Zhou, Ziyang Jiang, Jintao Ke
cs.LG · cs.AI
Tabular data generation supports analysis and decision-making when target-domain data are scarce, yet collecting complete target samples is often costly. A practical but underexplored setting provides only a few target records together with richer source data from a related domain. Existing few-shot tabular generators often either fit sparse target statistics directly, which can overfit incidental patterns, or reuse source-domain generators,...
-
49
Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting
Seunghan Lee, Jaehoon Lee, Jun Seo, Junhyeok Kang, Sangjun Han, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan...
cs.LG · cs.AI
The direction of change --- whether a series will move up or down --- is often as important as its exact value in decisiondriven applications such as risk management and financial forecasting. However, most forecasting losses optimize either point magnitude or shape and frequency structure, and none explicitly targets the direction of change. In this paper, we find that MSE-trained forecasters fail on the direction of small moves. To address...
-
50
WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model
Leyang Chen, Junyi Wu, Shaoqiu Zhang, Yulun Zhang
cs.LG · cs.CV
Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow. Existing caches reuse intermediate features, selectively update tokens, or reuse and extrapolate denoising outputs ac- cording to local drift or short native-space histories. These criteria can miss both approximation-induced latent transition defects that accumulate across skipped steps and phase- or...
-
51
tFUSOperator: Operator Learning for Transcranial Focused Ultrasound Digital Twins
Minjee Seo, Haris Ghafoor, Minju Seol, Seonaeng Cho, Kyungho Yoon
cs.LG · math.NA
Transcranial focused ultrasound (tFUS) requires accurate estimation of the intracranial acoustic field, which is distorted by skull-induced aberrations. Numerical solvers are accurate but computationally expensive for digital twins, where the field must be re-estimated repeatedly as treatment conditions change. Existing deep-learning surrogates are fast but typically use voxel-to-voxel regression on a fixed grid, with no mechanism reflecting...
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.