cs.LG · 2026-08-03 · No. 73
Machine Learning, 2026-08-03.
69 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
69 entries-
01
Freeze, Then Select: Structured Field Adapters and Stability-Validated Weak Selection for PDE Discovery from Sparse Observations
Juncheng Zhong, Chenghuang Shen, Jianfeng Liu, Zhengdong Xiao, Longjiu Luo, Qianrong Wang, Wenjun Xu, Wenlian Lu
cs.LG · math.NA
PDE discovery from sparse observations requires reconstructing a continuous field and selecting the correct differential terms. Our analysis of optimization paths in coupled neural PDE discovery reveals three behaviors: the exact support can persist to the end of training, appear only transiently, or fail to emerge. To decouple equation selection from neural optimization, we develop a freeze-then-select method combining a structured field...
-
02
GQ-FSL: Green Quantized Federated Split Learning
Idan Roth, Lutz Lampe
cs.LG · cs.DC · eess.SP
Deploying state-of-the-art deep neural networks (DNNs) at the wireless edge is severely bottlenecked by the strict energy and resource constraints of mobile devices. While federated split learning (FSL) mitigates on-device computation by offloading workloads to an edge server, this may introduce systemic overheads, while the continuous exchange of cut-layer data, and submodels still incurs significant energy consumption (EC). To address this,...
-
03
CENDRe: Concept Extraction with Natural Domain Representations
Antonia Holzapfel, Andres Felipe Posada Moreno, Sebastian Trimpe
cs.LG · cs.AI
Convolutional neural networks (CNNs) are widely used for time-series classification, but their deployment in critical domains requires understanding the temporal and spectral patterns that drive their predictions. Concept extraction (CE) methods identify such patterns by analyzing representations within the models' latent space. However, existing time-series CE methods have three limitations: they operate only in the time domain and overlook...
-
04
When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
Luca Viano, Antoine Moulin, Audrey Huang, Volkan Cevher, Philip Amortila, Dylan J. Foster
cs.LG · cs.AI · stat.ML
Imitation learning (IL)---training an agent to replicate expert behavior from demonstrations---underpins applications from robotics to language model training. Standard approaches such as Behavior Cloning (BC) are known to suffer from compounding errors and performance plateaus, particularly when the learner cannot perfectly represent the expert's policy (as is typical, e.g., in distillation). Two interventions are widely understood...
-
05
A Human-Centered Validation of the Explainability-Performance Coefficient
Christian Oliva, Luis F. Lago-Fernández
cs.LG · cs.AI · cs.CV
The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI). However, objectively evaluating explanation fidelity and aligning XAI metrics with human-centered understanding remain critical open challenges. In this work, we propose a model-agnostic metric, the EPC score, which is an extension of the Explainability-Performance Coefficient (EPC), that...
-
06
The Parts Are Greater Than the Sum: Automated Task Sequencing for Efficient Training of Multi-Policy LLMs
Jiajia Tang, Sizhe Yuen, Francisco Gomez Medina, Yali Du, Adam Sobey
cs.LG
Parameter-Efficient Fine-Tuning (PEFT) commonly adapts large language models using a single shared Low-Rank Adapter (LoRA). This shared optimization space often suffers from interference when adapting heterogeneous task sequences, leading to poor transfer and catastrophic forgetting. Existing approaches mainly improve adapter expressiveness by increasing parameter capacity or composing multiple adapters, yet they still rely on a shared...
-
07
Convergence and Regret of the Policy Gradient for Multi-Armed Bandits in Diffusion Environment
Yanwei Jia, Du Ouyang
cs.LG · math.OC
This paper studies the policy gradient update for a multi-arm bandit problem in diffusion environment that is described by a stochastic differential equation (SDE) under the continuous-time reinforcement learning framework by Wang et al. (2020), Jia and Zhou (2022b). With the logit parameterization for the stochastic policy, we show that it converges almost surely to the optimal arm under an arbitrary constant learning rate. Furthermore, we...
-
08
MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models
Boxiao Wang, Runxiang Wang, Kai Li, Chongming Li, Zhiwei Chen, Yifan Zhang, Jian Cheng
cs.LG · cs.AI
Symbolic Regression (SR) aims to discover analytical equations from observational data and plays a central role in scientific modeling. While recent Large Language Model (LLM) based approaches show promise, they face two limitations. First, they lack data analysis mechanisms for uncovering variable dependencies, which reduces the efficiency of equation discovery. Second, most methods rely on single-objective evaluation focused solely on...
-
09
Pyramidal Width Can Increase Under Vertex Insertion
Jinze Zhao
cs.LG
Lacoste-Julien and Jaggi conjectured in 2015 that the pyramidal width of a polytope cannot increase when a vertex is added, provided that every old point remains a vertex. We give an exact counterexample with six integer points in $\R^3$. For \[ P=\conv\{v_0,\ldots,v_4\},\qquad Q=\conv\{v_0,\ldots,v_5\}, \] where \[ \begin{aligned} v_0&=(-1,-3,-1), & v_1&=(3,2,-2), & v_2&=(0,2,1),\\ v_3&=(-1,-3,3), & v_4&=(-2,0,1), & v_5&=(-1,0,-2),...
-
10
A Neurosymbolic Approach for Explainable Early Diagnosis of Alzheimer's Disease
Ranveer Singh, Pranuthi Tenali, Saurabh Mathur, Ameet Soni, Vaishali Phatak, Karla Lynch, Daniel Murman, Matthew...
cs.LG
Identifying reliable Alzheimer's disease (AD) markers typically requires manual, labor-intensive transcription and expert analysis, limiting its scale. We introduce an automated pipeline that extracts qualitative knowledge about potential AD progression indicators directly from audio recordings of verbal fluency tests. Our method uses pretrained foundation models to process raw audio and extract clinically relevant variables to construct a...
-
11
TerraNova: A Foundation Model for the Anthropocene
Carlos Rodriguez-Pardo, Massimo Tavoni
cs.LG · cs.AI · cs.CY · econ.EM · stat.ML
A defining problem of the Anthropocene is to model the physical Earth and human societies as one coupled system, yet no learned representation spans their observational breadth. We argue the obstacle is geometric: the physical Earth is measured as continuous fields that ignore political borders, whereas societies are reported for administrative units. Earth-system foundation models serve the first geometry; coupling it to the second has...
-
12
The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting
Xiaotian Zhang, Lai Shun Chan, Yue Shang, Entao Yang, Ge Zhang
cs.LG
While neural networks are typically evaluated by their training and test performance, these metrics do not reveal how robust a learned representation is. Recent studies have shown that solutions occupying larger volumes in parameter space, as quantified by Boltzmann entropy, often exhibit superior generalizability compared to those reached by conventional optimization, a phenomenon known as the high entropy advantage. Here we ask whether this...
-
13
Transcript-Managed Transformers: Monotone Multi-Agent Collapse and Universality with Two Pop-Enabled Transcripts
Sergey Salishev
cs.LG · cs.FL · cs.MA
We study transcript management for fixed, finite-precision causal Transformers. A transcript is partitioned into channels of bounded blocks. Each transition consults a fixed visible suffix and may append one block, leaving the model, weights, and token protocol unchanged. The operation $P_c:=\PopContext(c)$ deletes the newest block on channel $c$ and exposes its predecessor. We model the layer by the Transcript-Managed Transducer $\TMTn{k}$:...
-
14
Adaptive FastOPD: Progress-Aware Rollout Horizon Expansion for Efficient On-Policy Distillation
Qian Tan, Huaifei Liang, Xuanyu Zhu, Lei Jiang, Yuqiang Li
cs.LG
On-policy distillation (OPD) provides dense teacher supervision along student-generated trajectories, but its online rollout process incurs substantial computational cost, particularly when a few long responses delay batch completion. Existing acceleration methods typically control rollout length using fixed budgets or absolute teacher--student agreement thresholds, which may not reflect learning progress across different models and training...
-
15
DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture Search
Jiayang Niu, Yan Wang, Jie Li, Ke Deng, Azadeh Alavi, Muhammad Usman, Yongli Ren
cs.LG · cs.AI
Reinforcement-learning-based quantum architecture search (RL-QAS) repeatedly optimizes a variational quantum eigensolver (VQE) after extending a circuit, although circuit construction and action legality are deterministic and known. We introduce DreamQAS, a model-based RL framework that preserves these exact circuit dynamics and learns only the expensive post-VQE feedback. A recurrent randomized-prior ensemble predicts an oracle-free score...
-
16
MolGVR: A Chemistry-Grounded Framework for Text-to-Molecule Generation
Qian Tan, Xuanyu Zhu, Lei Jiang, Zhonghang Yuan, Chen Zhang, Yuqiang Li
cs.LG
Text-to-molecule generation is typically formulated as a one-shot sequence generation problem, where a model directly maps target descriptions to molecular representations. However, molecular descriptions often contain informative structural constraints, and violating such constraints can change the molecular identity. This makes chemical verification and error correction important but underexplored. To fill this gap, we propose MolGVR, a...
-
17
Parameter-Free Heavy-Tailed Bandits
Gianmarco Genalti, Alberto Maria Metelli
cs.LG
Heavy-tailed distributions arise naturally in sequential decision-making problems such as financial investment, online advertising, and network management, where rare but extreme outcomes can dominate performance. Heavy-tailed bandits model online decision-making in these settings by assuming only that rewards $X$ satisfy $\mathbb{E}[|X|^{1+ε}]\leq u$, for some tail exponent $ε\in(0,1]$ and moment bound $u<+\infty$. However, most existing...
-
18
TFGformer: Multivariate Time Series Forecasting via Time-Frequency Graph Learning and Covariate Fusion
Yu Sun, Yuan Chang, Xiaohou Shi, Yan Sun
cs.LG · cs.AI
Large-scale multivariate time series from heterogeneous IoT sensors demand accurate long-term forecasting for resource scheduling and predictive maintenance. While recent time series foundation models exhibit strong generalization, they rely on static parametric knowledge and lack dynamic access to external historical patterns during inference. Retrieval-Augmented Generation (RAG) offers a potential remedy, yet its application to time series...
-
19
End-to-End Fairness Optimization with Fair Decision-Focused Learning
Yu Wang, Violet, Chen
cs.LG · math.OC
Many real-world systems rely on predictive models to inform decisions, and fairness concerns arise in both the prediction and decision stages. We introduce end-to-end fairness optimization (E2EFO) as a unifying framework that integrates fairness across the prediction-to-decision pipeline. We focus on resource allocation with group-based fairness: the prediction task estimates allocation impacts while limiting accuracy disparity across groups,...
-
20
Explore Beyond the Boundary Using Entropic Information
Bumgeun Park, Donghwan Lee
cs.LG · cs.AI
In reinforcement learning, exploration with sparse and delayed rewards presents a significant challenge due to the limited feedback available for guiding the learning process. Addressing this issue requires extensive exploration in the state space to discover valuable reward signals. In this paper, we propose Entropic Information for Exploration (ENTINEX), a novel method that enhances exploration by incentivizing agents to explore beyond the...
-
21
ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning
Xiyang Zhang, Hongzhi Wang, Yuanhe Tian
cs.LG
A routing decision can be revised at the next transaction, but a latched source exclusion persists across later decisions. We ask what evidence should authorize these unequal-persistence actions when finite-population auditing and learning share a budget. ALIVE (Action-Layered Intervention via Evidence) is an auditable control layer: one randomized without-replacement prefix supplies cached evidence, heuristic warnings drive non-latching...
-
22
OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference
Zhikang Xie, Xichen Ye, Yifan Wu, Haoshen Yu, Li chenan, Peizhu Gong, Weizhong Zhang, Cheng Jin
cs.LG
Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising. While cache-based strategies accelerate inference by reusing intermediate features, they largely rely on static, sample-agnostic schedules. We argue that this rigidity overlooks two facts empirically validated in this paper: (i) generation difficulty varies across prompts, requiring adaptive resource allocation--complex inputs demand more...
-
23
Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies
Jan Marius Stürmer, Jascha Knack, Tobias Koch, Andreas Weinmann
cs.LG · cs.SE
Large language models (LLMs) have demonstrated a strong ability to generate syntactically correct code from natural-language specifications. In this study, we explore how LLMs can be harnessed to automatically translate a neutral graph representation of fluid system models into executable code for two widely adopted simulation environments: the Python library WNTR and the Modelica Standard Library. We conduct a systematic comparison of ten...
-
24
Exploring Block Anomaly Detection In HDFS Log Data Analysis
WenYang Zhong, Tutut Herawan
cs.LG · cs.DC · cs.SE
In recent years, with the development of big data technology, increasingly more companies use HDFS for data processing and storage. As a result, the maintenance of distributed file systems has become an extremely important part of data management. As the function of server systems is becoming increasingly diversified and their services are becoming complex, the logs, recording real-time events make it easier for system operators to locate the...
-
25
Cross-Resolution Semantic Learning for Graph Domain Adaptation
Yingxu Wang, Haoze Huang, Zhongkai Zheng, Shangsong Liang
cs.LG
Graph Domain Adaptation (GDA) transfers predictive knowledge from labeled source graphs to unlabeled target graphs under distribution shift. Existing methods align representations or regularize graph structures, but do not explicitly model how class-discriminative knowledge learned at different source neighborhood ranges should be routed across target ranges. We call the neighborhood range encoded by a graph representation its propagation...
-
26
Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning
Douwe den Blanken, Martin Lefebvre, Charlotte Frenkel
cs.LG · cs.AI · eess.AS
With the ever-increasing pervasiveness of smart edge devices, the demand is growing for applications that can be tailored to users (e.g., custom keyword spotting) or patients (e.g., adaptive health monitoring). Yet, most edge devices rely on fixed inference algorithms and thus cannot learn on-device to personalize predictions. When they can, devices typically support only a specific learning scenario, such as few-shot learning (FSL): going...
-
27
Analysing User Reviews to Identify User Concerns Around Permissions in AI Apps
Babar Shah, Faheem Ullah, Myles Watkinson, Muhammad Moiz Khalid, Tehmina Karamat Khan, Muhammad Junaid
cs.LG
Artificial intelligence is increasingly embedded in everyday software, making its integration into mobile apps inevitable. However, AI mobile app developers are not always versed in security and privacy best practices, leaving users to monitor their own security and understand how apps use their data. App reviews capture real user experiences, helping others make informed decisions before downloading. This paper presents a machine learning...
-
28
Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification
Anders Jonsson, Emilie Kaufmann, Gianmarco Tedeschi, Lorenzo Steccanella
cs.LG
We present HBPI-UCRL, a model-based algorithm for hierarchical reinforcement learning (HRL) that learns high-level and low-level policies in parallel. HBPI-UCRL exploits the fact that a high-level transition corresponds to a multi-step transition at the low level. We introduce two conditions on the low-level dynamics that are sufficient to make parallel HRL learnable. When these conditions hold, we prove that HBPI-UCRL has a polynomial sample...
-
29
Assessing the Generalization of Graph Neural Networks for Fault Location Across Increasing Distributed Energy Resource Penetration Levels
Burak Karabulut, Olayiwola Arowolo, Carlo Manna, Chris Develder, Jochen L. Cremer
cs.LG · eess.SY
Accurate fault location is critical for distribution network reliability. However, increasing distributed energy resource (DER) penetration complicates fault location due to intermittent generation and bidirectional power flows that reshape fault signatures. Spatio-Temporal Graph Neural Networks (STGNNs) have shown promise by jointly modeling spatial and temporal dependencies, but their behavior under increasing DER penetration has not been...
-
30
UniPolymer: A Unified Framework for Property Prediction, Structure Recommendation, and Evaluation in Polyimide Design
Junquan Hu, Zhihui Wang, Peng Xu, Xinru Guo, Xintong Li, Kun Lu, Ben Fei
cs.LG
Designing polyimide structures with specific glass transition temperatures (Tg) is highly challenging. Existing methods primarily focus on target-conditioned generation, lacking an assessment of the consistency between the generated structure and the target properties. This leads to low-quality candidates deviating from the design objective entering subsequent processes, increasing invalid experiments and prolonging the development cycle. To...
-
31
Frugal Bayesian Optimization: Scalable Surrogates for Data- and Resource-Limited Discovery
Panagiotis Krokidas, Christoforos Rekatsinas, Vassilis Sioros, Grigorios M. Chatziathanasiou, Efi-Maria Papia,...
cs.LG · physics.chem-ph · physics.comp-ph
Bayesian Optimization (BO) is widely adopted for data-efficient optimization in scientific and engineering applications, yet its computational cost is rarely evaluated alongside optimization performance. Here we present a systematic, compute-aware study of BO that evaluates surrogate models along two axes: optimization quality and computational frugality. Across eight benchmark functions and nine real-world datasets spanning materials...
-
32
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Yifan Ding, Xincheng Wei, Yoshua Y. Li, Ziheng Li, Yuquan Lu, Siyu Zhang, Dongsheng Ma, Rongxiang Weng, Xunliang...
cs.LG · cs.AI
Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stronger teacher for a dense advantage but caps performance at teacher quality and discourages exploration beyond it. Their complementarity makes combining RLVR and OPD promising, but we find that fusing the two advantages with a fixed coefficient triggers entropy...
-
33
SERUM: State Extraction and Refinement for User Modeling
Andy J. Phu, James Mooney, Karin de Langis, Khanh Chi Le, Dongyeop Kang
cs.LG · cs.AI · cs.CV
Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow. However, building these models from raw, unstructured screen activity remains an open challenge. We present SERUM, a multi-pass framework that extracts finite-state behavioral models directly from unstructured egocentric video using hierarchical VLM annotation. Processing screen recordings through a sliding window, SERUM...
-
34
MBDiff: Multi-view Behavior-aware Diffusion Model for Probabilistic Utility Data Imputation
Rongchao Xu, Lin Jiang, Dahai Yu, Ximiao Li, Guang Wang
cs.LG · cs.AI
Utility data (e.g., electricity, water, and gas consumption), collected by ubiquitous sensors and embedded devices, often contains substantial missing values due to various factors such as device failures and data transmission issues. The data missingness can severely impact utility billing accuracy, hinder demand forecasting, and disrupt efficient utility supply management. As a result, utility data imputation has attracted much interest...
-
35
Implicit Machine Learning Force Fields Accelerate Molecular Dynamics Simulations
Johannes Maeß, Leon Werner, J. Thorben Frank, Winfried Ripken, Martin Michajlow, Joshua Futterer, Klaus-Robert...
cs.LG · cs.AI
We introduce implicit machine learning force fields (I-MLFFs), which replace explicit stacks of neural network layers with self-consistent fixed-point equations. In molecular simulations, this formulation enables intermediate representations to be reused across successive timesteps, thereby warm-starting force evaluation. The resulting models effectively combine the computational footprint of a shallow, single-layer MLFF with the...
-
36
HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators
Jiaquan Zhang, Shuxu Chen, Haifan Meng, Yi Lu, Zhihan Lyu, Fan Mo, Wei Dong, Yang Yang, Chaoning Zhang
cs.LG · cs.AI
Neural operators provide fast surrogates for time-dependent partial differential equations (PDEs) by applying a learned evolution operator recursively to its own predictions, but this autoregressive rollout feeds every prediction error back as input, so local errors accumulate. Existing rollout-training strategies reduce the mismatch between training inputs and self-generated states, yet their supervision still measures only the absolute...
-
37
PluRel-to-RDB-PFN: Schema-Guided Synthetic Relational Pretraining
Mohammad Sadeq Abolhasani, Viswanath Ganapathy
cs.LG
Relational Foundation Models (RFMs) require large-scale synthetic relational databases for pretraining, but existing approaches tightly couple data generation with the model training pipeline. We study whether PluRel, a general-purpose synthetic relational database generator, can serve as an external data source for RDB-PFN, a relational in-context learner originally pretrained with a 600K-task single-table warm-up followed by an...
-
38
Curriculum Matters: Data-Efficient Relational PFN Pretraining with Synthetic Data
Mohammad Sadeq Abolhasani, Viswanath Ganapathy
cs.LG · cs.DB
Relational Prior-Data Fitted Networks (PFNs) such as RDB-PFN approximate Bayesian inference over multi-table relational databases by pretraining on millions of synthetic tasks. We investigate three intertwined questions about this paradigm. First, can a structurally different synthetic generator PluRel substitute for RDB-PFN's prior? Second, how much does the order in which synthetic data is presented to the PFN affect downstream performance?...
-
39
StraightDP: Geometry-Aware Differential Privacy for Rectified-Flow Transformers
Xujun Che, Depeng Xu, Xintao Wu
cs.LG · cs.CR · cs.CV
Differentially private (DP) training of text-conditioned generative models suffers a utility cliff at strong privacy. We revisit this problem through the geometry of rectified flows: along the straight interpolation between noise and data, the Bayes-optimal velocity is governed to leading order at the noise end by a few class-conditional moments, and increasingly sample-specific structure matters toward the data end. StraightDP exploits this...
-
40
PiDDM: Physics-Informed Differentiable Degradation Modeling for Lithium-Ion Battery State-of-Health Prediction
Zeping Chen, Ruda Jian, Sachin Sigdel, Guoping Xiong, Jian-Xun Wang, Tengfei Luo
cs.LG
Accurate prediction of lithium-ion battery state of health (SOH) is essential for reliable energy storage operation. However, purely data-driven models may generalize poorly across cycling protocols and produce physically implausible behavior during long-term extrapolation. We developed a physics-informed differentiable degradation modeling framework (PiDDM) for battery SOH prediction. PiDDM incorporates empirical Arrhenius degradation...
-
41
What Is Missing in Surgical Risk Stratification and Outcome Prediction: A Scoping Review of End-to-End Machine Learning Approaches
Yizhi Dong, Yuhe Ke, Hairil Rizal Abdullah, Yucheng Xing, Kevan Kai Bing Teo, Ling Huang, Mengling Feng
cs.LG
Postoperative adverse events, including mortality and morbidity, remain a major global burden, many of which are preventable through early identification of high-risk patients and targeted perioperative care. Accurate risk stratification is therefore essential. With the growing availability of large-scale electronic health records (EHRs), machine learning (ML) provides a data-driven approach to model complex clinical patterns. However,...
-
42
DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation
Yuchen Xia, Qianguo Sun, Chao Song, Junlong Wu, Yiyan Qi, Yunjian Xu
cs.LG
On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias. However, in multi-turn agent scenarios, early student errors can lead a trajectory away from the teacher's familiar domain. Existing curriculum learning methods regulate how much teacher support is used according to training progress, but cannot determine when it is needed. In light of this, we propose DASH-OPD, Discrepancy-Aware Switching with...
-
43
Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients
Shengkun Zhu, Jinshan Zeng, Zhihua Allen-Zhao, Mayi Xu, Quanqing Xu, Wei Ren, Qiang Yang, Yang Liu
cs.LG · cs.AI
Federated learning of foundation models faces a fundamental resource-asymmetry challenge: the institutions holding the most valuable domain-specific data cannot host billion-parameter models. Existing heterogeneous federated approaches attempt to bridge this gap through parameter-efficient tuning, model pruning, or knowledge distillation, yet each trades away a critical property, whether full-model memory reduction, architectural...
-
44
Benchmarking Frontier Large Language Models Against Official Crash Database Coding Using Police Crash Narratives
Sudhir Bharati, Rajendra K C Khatri, Sudip Bharati
cs.LG · cs.AI
Police crash narratives contain information that may supplement structured crash databases, but manual review is labor-intensive and it remains unclear how well large language models (LLMs) reproduce official crash coding. This study benchmarked six frontier LLMs by comparing narrative-derived crash attribute codes with corresponding fields in the Arkansas fatal-crash database. The analysis linked 5,587 fatal-crash narratives with 5,889...
-
45
Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search
Hanxiao Lu, Tianyi Zhang
cs.LG · cs.AI · cs.MA
Multi-agent systems (MAS) are increasingly deployed to solve complex tasks. In case of incorrect or unsatisfactory outputs, users have to manually locate agent mistakes by inspecting agent trajectories (i.e., {\em failure attribution}) and provide feedback to refine the outputs (i.e., {\em repair}). Despite some recent work in MAS failure attribution, automated mechanisms to recover from such mistakes remain largely unexplored. To bridge this...
-
46
Who Wins Where? Conformal Model Comparison for Local Superiority
Yi Zhou, Baishi Li, Xuan Yao, Ke-Wei Huang
cs.LG
Standard model comparison is global, aggregating losses across the covariate space to declare a single winner. This can obscure heterogeneous performance, where different models are preferable in different regions. We introduce conformalized local model comparison, a split-sample framework for constructing calibrated local best-model maps. Given a model comparison score, such as the difference between two squared losses, the method uses three...
-
47
Learning Lookahead Lemmas for Neural Network Verification
Liam Davis, Haoze Wu
cs.LG · cs.AI · cs.LO
State-of-the-art neural network verifiers use the branch-and-bound procedure as their core solving mechanism. We introduce an inprocessing framework for neural network verification driven by the lookahead procedure. Under this framework, lookahead derives new lemmas over the phases of unstable ReLUs, which are collected into an implication graph that is used to prune the search space and vivify boolean cuts. We instantiate the framework in...
-
48
DFSC: Error-Controlled Differentiable Mittag-Leffler Propagation for Fractional Scientific Machine Learning
Ning Hu, Haitao Duan, Shuqun Li, Chuyang Hu
cs.LG
Fractional scientific machine learning requires numerical operators that can be differentiated, batched, accelerated, and composed with neural networks. When the dominant linear fractional evolution is known through a Mittag-Leffler propagator, repeatedly reconstructing that response with a history solver or relearning it from data is unnecessary. We present DFSC, a PyTorch environment organized around the Mittag-Leffler Spectral Layer...
-
49
Dynamics-aware identification of governing equations from sparse and noisy data
Pongpisit Thanasutives, Yoshinobu Kawahara
cs.LG · math.DS
Sparse identification of nonlinear dynamics (SINDy) and PDE functional identification (PDE-FIND) recover parsimonious ordinary and partial differential equations (ODEs and PDEs) from data. However, sparse and noisy temporal measurements can make derivative estimates unreliable. To address this problem, we evaluate Koopman-based upsampling techniques implemented with dynamic mode decomposition (DMD), extended DMD (EDMD), and optimized DMD....
-
50
SILVA Networks as Structured Implicit Layers and Vector Attractors via Dynamic Interaction Fields
Jose Luis Lima de Jesus Silva
cs.LG · cs.NE
Many learning problems require representations that reconcile direct input, nearby structure, and broader context. In implicit neural layers, these influences are usually absorbed into a single fixed-point update, making it hard to identify what enters from the stimulus, what propagates locally, what comes from global context, and what is produced by solver dynamics. Here we introduce SILVA Networks, Structured Implicit Layers and Vector...
-
51
Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models
Yi Wang, Jitao Zhao, Di Jin, Dongxiao He
cs.LG
Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for enabling knowledge transfer across diverse domains. Unlike traditional graph learning methods that are typically designed for in-domain settings, GFMs aim to learn transferable knowledge that can generalize to unseen graph domains. However, unlike language or visual data, graphs lack intrinsic and unified representation units, such as tokens in language and...
-
52
Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates
Weiyi He, Yuping Lin, Jiliang Tang, Yue Xing
cs.LG · cs.AI
Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especially for large language models (LLMs). While existing mitigation strategies, e.g., latent adversarial training (LAT), have been developed, they still incur a high computational cost. In this work, we comprehensively investigate computation-efficient strategies to speed up LAT from two...
-
53
Mining Verdict Boundaries for Neural Network Verification
Jiawei Ren, Guanqin Zhang, Zhenya Zhang, Yulei Sui
cs.LG · cs.LO · cs.SE
Branch and Bound (BaB) aims to achieve complete verification of neural networks by adaptively partitioning the problem and applying off-the-shelf verifiers to subproblems. Its problem-splitting history can be represented as a tree, where each subproblem corresponds to a child node. A key problem of BaB lies in searching for the verdict boundaries across all the paths that divide the verified and unverified subproblems. We observe that the...
-
54
Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination
Jingwen Fu, Zhen Liu, Yuhan Liu, He Zhang, Nanning Zheng
cs.LG
Large language models (LLMs) are increasingly used to solve complex problems by searching over program space, offering a general paradigm for scientific problems that can be naturally represented and solved as programs. Despite recent progress, identifying effective optimization directions for a candidate program remains challenging. By analogy with automatic differentiation, existing methods typically guide the search using a textual...
-
55
Shapley-Value-Based Feature Attribution for Data Masking
Xinxue, Qu, Francis Bilson Darku, Hong Guo
cs.LG
Despite its many benefits, widespread access to individuals' personal data also causes severe privacy concerns for consumers, companies, and policymakers. This study proposes a novel framework that adapts the Shapley-value-based feature attribution approach to the problem domain of data privacy by capturing the two crucial dimensions of data privacy---disclosure risk and data utility. Our proposed framework takes a holistic view of data...
-
56
FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents
Nitish Nagesh, Mahdi Bagheri, Amir M. Rahmani
cs.LG
Synthetic tabular data is increasingly used in privacy-preserving data sharing, data augmentation, and to mitigate downstream classifier bias. State-of-the-art tabular diffusion models such as TabDDPM and TabSyn achieve excellent distributional fidelity but offer no mechanism for fairness; conversely, fairness-aware tabular generators (DECAF, FairTGAN, FairTabDDPM) impose explicit fairness penalties at training time, yielding modest fairness...
-
57
Latent Lie-Poisson Neural Networks (LLPNNs): Discovering the motion of Lie-Poisson systems through observable data and latent dynamics
Vakhtang Putkaradze
cs.LG · math.DS · math.OC
Structure-preserving neural networks are essential for the long-term prediction of Hamiltonian systems from data. Many important Hamiltonian systems in mechanics and control admit symmetry reduction to Lie--Poisson systems, including rigid bodies, underwater vehicles, fluids, plasmas, and optimal control problems. A fundamental challenge in learning such systems is that their dynamics evolve in momentum variables that are typically...
-
58
Learning Optimal Dynamic Matching via Graph Neural Networks
Genta Okada, Shunya Noda, Junpei Komiyama, Akira Matsushita
cs.LG · cs.GT · econ.TH
Dynamic matching markets require decisions about whom to match and when: matching now yields value but removes participants who may create better future opportunities. We develop a value-based reinforcement-learning framework for this problem on finite, evolving weighted graphs. We study an infinite-horizon continuous-time model with stochastic arrivals, node-type transitions, edge realizations, and exogenous exits. We prove an event-time...
-
59
Gated Q-learning: Add Off-Policy Bias to Taste
Brett Daley
cs.LG · cs.AI
Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge. For 30 years, practitioners have been limited to a binary choice: eliminate the bias at the cost of severely truncated eligibility traces (Watkins' Q($λ$)), or ignore the bias to learn faster while injecting detrimental errors into the value estimates (Peng's Q($λ$)). Modern...
-
60
Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds
Yefan Tao, Gerald Friedland, Madhusudhanan Chandrasekaran, Luyang Kong
cs.LG
Reflection, the ability to revisit and revise prior reasoning, is central to how humans improve their answers. Large language models (LLMs) are increasingly prompted to "reflect," yet whether this resembles human revision remains unclear. We introduce the Human-LLM Reflection Framework (HRF), a controlled two-pass protocol comparing human and LLM revision under identical conditions across self-, peer-, and cross-agent settings. Using an...
-
61
Adaptivity via a Parallel Architecture for Stochastic Gradient Methods Adaptivity via a Parallel Architecture for Stochastic Gradient Methods Adaptivity via a Parallel Architecture for Stochastic Gradient Methods
Bin Fu
cs.LG · cs.AR · math.OC
We develop a parallel framework that assembles static gradient methods to achieve better adaptivity. A static gradient method, denoted by $\mathrm{GD}(x_0,T)$, takes as input an initial point $x_0\in\mathbb{R}^n$ and $T\in \mathbb{R}^+$ specifying the number $\floor{T}$ of iterations. The step size is chosen as $s=S(T)$, where $S(\cdot)$ is a predetermined function of $T$. The method then performs the iterations $ x_{i+1}=x_i-\fracη{s}\cdot...
-
62
Fast Rates for Swap-Agnostic Learning of Proper Losses
Princewill Okoroafor
cs.LG
Swap-agnostic learning strengthens classical agnostic learning by allowing the comparator to select a different hypothesis on each level set of the learner's predictions. This benchmark captures prediction-dependent postprocessing, but appears to require solving a separate agnostic-learning problem for every possible prediction value. We show that, for proper losses, these prediction-level comparisons can instead be controlled jointly. Our...
-
63
An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks
Sheng Lun Christine Cao, Destenie Nock, Alex Davis
cs.LG
Discrete choice modeling is a common tool used for preference elicitation during policy-making, but this is typically done through parametric models. Machine learning can push the boundaries of discrete choice modeling for policy-based preference elicitation by adopting a data-driven approach or learning individual preferences. However, there is limited knowledge of how well machine learning methods can estimate individual discrete choice...
-
64
Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity
Naman Saxena, Mudit Gaur, Vaneet Aggarwal
cs.LG · cs.AI
Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hierarchical task decomposition, and reinforcement learning from human feedback (RL-HF). Most of the bilevel RL algorithms are either not scalable because of using hypergradient with Hessian, or they suffer from high sample complexity because of using penalty-based...
-
65
Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations
Konur Tholl, François Rivest, Mariam El Mezouar, Adrian Taylor, Ranwa Al Mallah
cs.LG
Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication. ACO applications commonly employ Reinforcement Learning (RL) agents to learn defensive behaviors through interaction with environments. However, RL agents typically require extensive exploration during training, often resulting in unstable behavior and poor initial decision-making before...
-
66
Representations from Pretrained Machine-Learning Interatomic Potentials as Coarse Coordinates for Material Generation and Evaluation
Paul Hagemann, Katharina Ueltzen, Simon Müller, Janine George, Philipp Benner
cs.LG · cond-mat.mtrl-sci
Generative machine learning is increasingly used for inorganic crystal structure generation. Most models and the corresponding evaluation approaches rely on simple forms of crystal structure representation. In this paper, we showcase the power of atom-averaged features from pretrained Machine-Learning Interatomic Potentials (MLIPs), such as MACE, for such tasks. We first introduce a distance measure that assesses the output of material...
-
67
Feature Interaction Modeling for Physics-Informed Neural Networks and Neural Operators
Quan Gu, Hongxia Liu
cs.LG
This work embeds feature interaction modules derived from factorization machines (FMs) into physics-informed neural networks (PINNs) and neural operator learning, to enhance model expressiveness for solution manifolds of parameterized partial differential equations (PDEs). Motivated by the second-order Taylor expansion of multivariate functions to characterize variable couplings, we first propose FM-PINN. It explicitly captures...
-
68
TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning
Brendan Kennedy, Tegan Emerson, Gregory Roek, Emilie Purvine, Henry Kvinge
cs.LG
Over the last decade, neural networks have been applied to an increasingly diverse range of applications, including data with rich geometric, topological, or symmetry-related structure. As a result, researchers have increasingly drawn inspiration from topology, algebra, and geometry. Despite this rich algorithmic development, the supporting software ecosystem remains fragmented. Many important methods exist only as research prototypes in...
-
69
Mirror Learning
Yunpeng Liu, Matthew Niedoba, Oluwanifemi A. Adekanye, Jason Yoo, Yingchen He, Berend Zwartsenberg, Frank Wood
cs.LG · cs.CV · cs.RO
We investigate imitation learning through the lens of third-person observation and propose a framework for mirror learning: acquiring actionable policies from passive observation. While behavior cloning (BC) excels under dense, well-aligned first-person data, it fundamentally fails to leverage the rich observational signals arising from third-person demonstrations that humans and animals routinely exploit. We introduce a method that composes...
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.