cs.LG · 2026-07-23 · No. 62
Machine Learning, 2026-07-23.
57 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
57 entries-
01
PG-KINN: A Physics-Informed Petrov-Galerkin Kolmogorov-Arnold Network for Solving Forward and Inverse PDEs
Amirhossein Sadr, Nima Soltani, Vahideh Moghtadaiee, Aida Pakniyat, Dara Rahmati, Saeid Gorgin
cs.LG · math.NA
Physics-informed learning of partial differential equations (PDEs) has been dominated by multilayer perceptrons (MLPs), whose spectral bias and dense parameterization limit both accuracy and interpretability. Kolmogorov Arnold Networks (KANs) mitigate these limitations because their learnable spline activations are structurally aligned with the piecewise-polynomial bases of classical discretizations. However, the way a PDE is cast into a loss...
-
02
Online Variance Reduction for Domain Adaptation on Streaming Data
Andrea Napoli
cs.LG
This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions. Although various offline SVR algorithms for these losses have been proposed, these are incompatible with online, distributed, or incremental learning settings. This paper presents Adaptive vaRiance Reduction via Online reWeighting (ARROW), the first online SVR algorithm for the MMD and...
-
03
Variance-reduced Domain Adaptation using Paired Sampling
Andrea Napoli
cs.LG
Correlation alignment and the maximum mean discrepancy are two widely used distribution-matching frameworks for unsupervised domain adaptation (UDA). However, high variance in these losses has been shown to undermine their effectiveness in minibatch optimisation settings. Furthermore, the losses lack finite-sum structure, which renders them incompatible with classical stochastic variance reduction (SVR) methods. This paper proposes Paired...
-
04
Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling
Somesh Pratap Singh, Govinda Anantha Padmanabha, Jingye Tan, Steven Yang, Reese E. Jones, D. Thomas Seidl, Nikolaos Bouklas
cs.LG · physics.comp-ph
Constitutive modeling under uncertainty remains a central challenge for reliable mechanics simulations, particularly when the available stress-deformation data are sparse, noisy, or heterogeneous. We propose interval and fuzzy physics-augmented neural networks (iPANNs and fPANNs) for uncertainty-aware hyperelastic constitutive modeling. iPANNs learn sparse lower, mean, and upper free energy density branches whose stresses, obtained by...
-
05
Multi-modal transformer for signal classification in nanopore blockade experiments
Sandro Kuppel, Julian Hoßbach, Samuel Tovey, Christian Holm
cs.LG · physics.comp-ph · q-bio.BM
Nanopore devices have emerged as powerful tools for single-molecule sensing, with potential for rapid, portable diagnostics. They detect changes in ionic current as analytes enter nanometer-scale pores, providing a means of identifying diverse biomarkers from their characteristic signal patterns. However, these signals are highly complex, and reliably assigning them to specific molecules remains a major challenge. Here, we address this by...
-
06
Classical Hardware Acceleration of Quantum Autoencoders for Real-Time Anomaly Detection in Collider Experiments
Ivan Ge, Sagar Addepalli, Abhilasha Dave, Julia Gonski
cs.LG · hep-ph · physics.ins-det
Quantum machine learning (QML) algorithms in high energy physics (HEP) can efficiently represent and leverage long-range, high-order correlations in high-dimensional collider data, potentially with fewer parameters and favorable scaling relative to classical models. Deployment of QML in real-time collider applications such as trigger systems requires the ability to emulate and compile quantum circuits classically, then synthesize the...
-
07
The Blessing of Dimensionality: How Near-Orthogonality in High-Dimensional Spaces Explains Temporal Portability
Abigail Woodring, Adrian Chan, Rana Muhammad Shahroz Khan, Sukwon Yun, Chau-Wai Wong, Tianlong Chen
cs.LG · cs.CL
Fine-tuning has been widely used to adapt large language models (LLMs) for domain-specific tasks. Parameter efficient fine-tuning (PEFT) methods such as low-rank adaptation (LoRA) are frequently used to reduce computational costs. PortLLM is a training-free and data-free scheme used to adapt LLMs after continual pretraining. Although the initial PortLLM results show that LoRA patches exhibit short-term temporal portability, the long-term...
-
08
Interpretable Fuzzy Rule-Based Regression Extension for Ex-Fuzzy Library
Cayan Deniz Kucuktopana, Javier Fumanal-Idocin, Richard Pitts, Javier Andreu-Perez
cs.LG
Machine learning models achieve high predictive accuracy in regression tasks, but their deployment in safety-critical and regulated domains requires interpretability. While fuzzy rule-based systems offer transparent, linguistically explicit interpretable models, Mamdani-style fuzzy regression remains underrepresented in modern machine learning software libraries. This paper presents an interpretable regression extension for the Ex-Fuzzy...
-
09
Breaking the $T^{3/4}$ Barrier for Regret Minimization With Bi-Dimensional CDFs
Matteo Castiglioni, Anna Lunghi, Alberto Marchesi
cs.LG
We study regret minimization for learning CDF-related objectives of the form \[ g(x)\cdot\mathbb{P}_{X\sim\mathcal{D}}(X\le x), \] over $[0,1]^2$, where $g$ is a known Lipschitz function and $\mathcal{D}$ is an unknown distribution. At each round $t$, the learner selects a point $x_t$ and observes the binary feedback $\mathbb{I}(X_t\le x_t)$, where $X_t\sim\mathcal{D}$. We design an algorithm achieving regret...
-
10
PhaseAware: Interpretable Human-in-the-Loop Rehabilitation Scoring with Boundary Monitoring
Yankai Zheng, Yuhe Liu, Yuxin Ma, Tianci Xue, Jiayuan Tian, Yu Fu, Yuxuan Hu, Jianing Wang, Zichun Xiao, Junya Mu, Shaohui Ma
cs.LG
Rehabilitation scoring systems are most useful when their outputs can be reviewed and interpreted within clinical workflows. This study presents PhaseAware, a compact framework for continuous rehabilitation quality assessment that combines a temporal backbone with phase- and body-group descriptors through a backbone-conditioned gated residual pathway. The model was evaluated on the UI-PRMD deep-squat protocol and further tested on the KIMORE...
-
11
PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling
Shiyuan Luo, Runlong Yu, Chonghao Qiu, Yue Qin, Rahul Ghosh, Robert Ladwig, Paul C. Hanson, Yiqun Xie, Xiaowei Jia
cs.LG
Accurate modeling of environmental systems is fundamental to scientific understanding and decision-making, yet remains challenging because observations are limited and physical dynamics vary across systems. Retrieval-augmented approaches offer a natural path to transfer knowledge across systems, but standard embedding-based retrieval does not guarantee consistency of underlying physical processes, since scenarios with similar embeddings may...
-
12
User-Centric Modeling of Transactional Sequences with Explainable State Space Models
Ivan Palagin
cs.LG
We propose a hybrid approach for user-centric modeling of transactional event sequences that combines contrastive representation learning (CoLES) with State Space Models (SSMs). While contrastive methods yield high-quality compressed user representations, existing encoders -- RNNs and Transformers -- suffer from vanishing gradients or quadratic complexity, respectively. Mamba, a selective SSM, efficiently handles long-range dependencies but...
-
13
ELSAA: Efficient Low-Rank and Sparse Attention Approximation for Training Transformers
Mahdi Heidari, Mohammad Mahdi Rahimi, Jaekyun Moon
cs.LG · cs.AI
The quadratic $N\times N$ attention score matrix remains a central obstacle to extending Transformers to longer input lengths. Existing efficient attention methods usually reduce this bottleneck by either imposing sparsity, so that each query attends to only a small subset of keys, or by using low-rank/kernel sketches, so that global interactions are compressed into a lower-dimensional representation. We propose \emph{ELSAA}, an efficient...
-
14
The Quadrilateral Loss: Additivity as a Measurable Behavior of Dense Neural Networks
Antonio Di Cecco
cs.LG · cs.AI
Additive models buy interpretability by forbidding feature interactions, a constraint that neural instantiations enforce architecturally. We introduce the quadrilateral loss, a differentiable penalty that treats additivity as a measurable behavior instead: a second-order mixed difference on pairs of training points swapping one coordinate, which vanishes if and only if the coordinate carries no interaction, remains informative for...
-
15
OLEDLM: A Unified Language Model for OLED Molecular Design
Fukang Wen, Yuchong Tang, Jingyuan Li, Beichen Wang, Yixuan Jiang, Xiaoyi Jiang, Yaxuan Liu, Shunyu Wang, Zuoqiang...
cs.LG
The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent quantum-chemical constraints, and a scarcity of labeled data. Although the question of OLED generation is important, few models have been trained effectively for this specific domain. We propose an inverse molecular design framework based on causal language models: given target optoelectronic...
-
16
On Optimization Complexity of Second-Order Certified Unlearning
Nikita Doikov, Anastasia Koloskova
cs.LG · math.OC
We study machine unlearning: the removal of memorized training data from a trained model. Specifically, we investigate the algorithmic complexity of certified unlearning from an optimization perspective. We formalize the goal of an unlearning algorithm as simultaneously achieving certified unlearning and optimization accuracy. Utilizing the notion of uniformly convex regularizers, we prove new bounds on the distance between initial and...
-
17
Instance Hardness-Based Relevance for Imbalanced Regression
Vitor M. Leitao, Juscimara G. Avelino, George D. C. Cavalcanti, Rafael M. O. Cruz
cs.LG
Imbalanced regression problems arise when the target variable has an asymmetric distribution, resulting in underrepresented value ranges in the dataset. Traditional approaches for identifying rare instances rely on a relevance function that assigns higher importance to specific regions of the target distribution. However, the effectiveness of imbalance-aware learning methods depends strongly on how relevance is defined. In more complex...
-
18
Self-organizing Architecture of Receptron Units: a Hardware-Aware Framework for Edge Intelligence
Stefano Radice, Ludovico Casaccia, Riccaro Emanuele Beccalli, Bruno Paroli, Paolo Milani
cs.LG · cs.ET
The growing demand for intelligent processing at the edge of IoT networks is constrained by the severe computational and memory limitations of microcontroller units, which render impractical conventional deep learning approaches. We propose a neuromorphicinspired classifier based on the Receptron model, a single-unit architecture capable of implementing non-linearly separable decision boundaries, without resorting to multi-layer networks. The...
-
19
Local Stability and Gaussian Smoothing of Quantized Neural Networks
Sergey Salishev, Anton Makarov, Oleg Granichin
cs.LG · eess.SY · math.OC
We study Gaussian averaging as a smooth surrogate for quantized neural models. Under bounded local oscillation, we derive a local dimension-dependent bound on |f-g|, linking Gaussian smoothing to the stability analysis of discontinuous networks. We compute closed-form Gaussian averages of the rectified linear unit (ReLU) and sign activation functions, and illustrate the mechanism on a high-dimensional binary perceptron, where...
-
20
Active Inference as a Convex Markov Decision Process
Nikola Milosevic, Nicolás Hinrichs, Nico Scherf
cs.LG · cs.AI · stat.ML
Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle. We frame AIF as policy optimization and show that, for closed-loop control policies, EFE minimization can be formulated as a convex Markov decision process (MDP). In this formulation, the pragmatic terms are linear in the predictive state marginals and therefore...
-
21
CURED: Creating, Understanding, and Repairing Errors Demonstrator
Nicholas Chandler, Sebastian Jäger, Philipp Jung, Felix Bießmann
cs.LG
Detecting and cleaning errors in tabular data is a prerequisite for data intense software applications. Recent research at the intersection of Machine Learning (ML) and Database Management Systems (DBMS) highlights the potential of statistical learning algorithms for error detection and cleaning. This paper combines our recent work on ML-based data cleaning and error models in a unified demonstrator. The web application allows users to upload...
-
22
Autonomous Collaborative Learning Among an Ensemble of Tsetlin Machines with Consensus-Based Inference
Yehuda Rudin, Osnat Keren, Michal Yemini, Alexander Fish
cs.LG · cs.MA
Tsetlin Machine (TM) is a rule-based machine-learning algorithm comprising collectives of two-action Tsetlin Automata (TAs) that cooperatively form conjunctive logical clauses from Boolean inputs through stochastic feedback. Although few recent studies have examined TM Federated Learning, the broader area of distributed and decentralized TM learning has not received much attention in the existing literature and warrants further exploration....
-
23
Co-Evolving LLM Evaluators and Policies via DynamicRubric
Beining Wang, Weihang Su, Hongtao Tian, Hao Kong, Tao Yang, Ting Yao, Qingyi Pan, Yueyue Wu, Qingyao Ai, Min Zhang, Yiqun Liu
cs.LG · cs.AI
Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models. As policies improve, these sampled responses become close in quality. These close candidates create a bottleneck for policy optimization: collapsed relative evaluator score gaps yield weak or misleading policy supervision. We theoretically characterize why these gaps matter through a probability allocation view,...
-
24
Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment
Farnaz Faramarzi Lighvan, Lynn Houthuys
cs.LG
AI-based recruitment systems that rely on machine learning models trained on historical CV data, risk perpetuating and amplifying social biases. A key challenge arises in unstructured CV text, where pre-trained language model embeddings may infer sensitive attributes such as gender even after explicit indicators are removed. In this paper, we evaluate nine pre-trained embedding models on the synthetic FairCVdb dataset, analyzing the...
-
25
Test Case Prioritization for DNNs via Neural Collapse Instability
Chunyu Liu, Mingyuan Li, Yang Li, Wenmin Li, Fei Gao, Tengfei Tu, Su-Juan Qin
cs.LG · cs.AI · cs.SE
With the widespread deployment of deep neural networks (DNNs) in safety-critical domains, reducing the cost of model validation under limited testing budgets has become increasingly important. Existing test case prioritization techniques often rely on single-checkpoint confidence signals derived from output probabilities. However, DNNs can be confidently wrong, and the confidence margin between the predicted and competing classes is...
-
26
Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models
Luukas Peräkylä, Fahad Sohrab, Ville Hautamäki, Merja Heinäniemi, Sui Huang, Pekka Abrahamsson
cs.LG
Short-term Heart Rate Variability (HRV) forecasting could provide clinicians with actionable lead time for detecting autonomic dysfunction and adverse cardiac events. Consumer wearable devices generate fragmented, artifact-rich HRV signals that challenge conventional forecasting approaches. In this study, we evaluated the forecasting ability of three Time Series Foundation Models (TSFMs), TimesFM, Chronos, and MOIRAI, against traditional...
-
27
Generalized Kalman filter based temporal difference reinforcement learning
Vasos Arnaoutis, Eric Lutters, Bojana Rosić
cs.LG · cs.CE
In this paper, we present a generalized temporal-difference (TD) reinforcement learning framework based on the theory of conditional expectations. The value and action-value (Q-value) functions are treated as uncertain quantities, and their estimation is formulated as a stochastic inference problem. Unlike classical Kalman-based temporal-difference learning, which relies on linear-Gaussian assumptions, the proposed formulation is derived...
-
28
Post-Training in Time Series Foundation Models: A Unifying Framework
Shifeng Xie, Ambroise Odonnat, Zehao Xiao, Lei Zan, Malik Tiomoko, Lujia Pan, Themis Palpanas, Boris N. Oreshkin,...
cs.LG · cs.AI
Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deployment. Bridging this gap requires further intervention to handle domain shift, task heterogeneity, limited supervision, and computational constraints, which motivates post-training as a broad class of methods to adapt, augment, compose, calibrate, or specialize...
-
29
Good Practice Guide for quantifying uncertainties for machine learning models applied to photoplethysmography signals
P. Harris, C. Bench, M. Rinkevičius, V. Marozas, L. Coquelin, A. Thompson, M. Nandi, U. Hackstein, P. J. Aston
cs.LG
This Good Practice Guide presents work done in the QUMPHY project (Uncertainty quantification for machine learning models applied to photoplethysmography signals) that considered both machine learning and uncertainty quantification for problems which used photoplethysmography (PPG) signals from wearable devices as input. It provides high-level guidance on what types of machine learning model might be used and how different models compare when...
-
30
Time Series Network Utilization KPI Forecasting Using Advanced AI/ML Models
Niraj Gadhe, Kirti Bhardwaj, Moulik Jain, Shubhi Sharma, Vinay Saini
cs.LG · cs.AI
The rapid proliferation of data-intensive applications, cloud infrastructure, and IoT ecosystems has made proactive resource provisioning critical for maintaining optimal network performance. However, network administrators face a constant battle against capacity constraints, where traditional reactive approaches fail to accurately anticipate traffic fluctuations. This inability to foresee demand leads to costly over-provisioning, unexpected...
-
31
Nonlinear Bias-Compensated Adaptive Filter and Its Application for Time-Series Prediction
Yi Peng, Haiquan Zhao, Jinhui Hu
cs.LG · eess.AS
Most existing nonlinear adaptive filtering algorithms only account for output noise, neglecting the fact that input noise is also prevalent in practice. Although the recently proposed bias-compensated kernel least mean square (BCKLMS) algorithm addresses input noise in the nonlinear errors-in-variables (EIV) model, it still suffers from two major limitations. First, the use of a fixed-size dictionary restricts network growth but also prevents...
-
32
Local Causal Structure Learning in the Presence of Latent Variables and Selection Bias
Zheng Li, Hao Zhang, Ruxin Wang, Ruichu Cai, Kun Zhang, Feng Xie
cs.LG
Discovering the direct causes and effects of a target variable from observational data is a fundamental problem in causal discovery, with broad applications in domains such as gene regulatory analysis and biomedical research. Existing causal discovery methods either learn a global causal structure, which incurs substantial computational cost, or assume the absence of latent variables and selection bias, assumptions that are often violated in...
-
33
Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation
Luca Scionis, Luca Melis, Maura Pintor, Fabio Brau, Ambra Demontis, Giorgio Fumera, Fabio Roli, Battista Biggio
cs.LG · cs.CR
Adversarial robustness is commonly evaluated with predefined attack ensembles, such as AutoAttack, at a single perturbation budget $\varepsilon$ and on a selective choice of perturbation norms. We argue this formulation is fundamentally limited. First, robustness--perturbation curves may intersect or decay at different rates across models, making single-$\varepsilon$ rankings unstable. Second, current ensembles provide no evidence of...
-
34
Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence
Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du
cs.LG · stat.ML
We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$. We propose a new algorithm and prove a regret upper bound \[\tilde O(\sqrt{SAK}+S^8A^3)\] with failure probability $δ$, where $K$ is the number of episodes and $\tilde O(\cdot)$ hides $\mathsf{poly}\log(S,A,K,1/δ)$. Thus, the regret is...
-
35
Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models
Yurong Liu, Yeye He, Haoyu Dong, Junjie Xing, Shi Han, Dongmei Zhang, Surajit Chaudhuri
cs.LG · cs.AI · cs.CL · cs.DB
Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise in predicting missing values in tables, by reasoning holistically across rows and columns, they are costly to deploy at scale and tend to be overconfident, often generating hallucinated or false-positive predictions. In this paper, we observe that achieving high-precision missing-value prediction...
-
36
OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization
Kavin Aravindan, Arihant Rastogi, Aadi Prasad, Krishak Aneja, Saiyam Jain, Vaishnavi Shivkumar, Ponnurangam Kumaraguru
cs.LG · cs.AI
Activation steering provides a lightweight mechanism for controlling large language models at inference time, but steering vectors can have unintended externalities: utility vectors may weaken safety behavior, while refusal vectors may induce over-refusal on benign prompts. We introduce OPIUM (Optimizing Protected Injections via Utility Manifolds), a training-free method for sanitizing steering vectors through representation matching. Given...
-
37
An Isotropy-Preserving Spectral Cap for Muon: Theory and Three Case Studies
Jiachun Li
cs.LG · cs.AI
Muon and related matrix-sign optimizers are increasingly used to pre-train large language models, but their effect on the internal geometry of individual weight matrices is not well understood. This preliminary report proposes a unified framework built on a single idealizing assumption -- exact scale invariance of the loss under weight rescaling, which holds approximately in normalization-heavy networks. Under this assumption, plain SGD...
-
38
AlphaRoute: Large Language Models as Semantic Optimizers for Multi-Objective Routing
Kabir Murjani, Mishri Bhavsar, Manish I. Patel, Jonti Talukdar
cs.LG · cs.AR
Very Large Scale Integration (VLSI) global routing is an NP-hard combinatorial optimization problem requiring signal net assignment across capacity-constrained 3D grids while minimizing congestion, wirelength, and via transitions. Because traditional heuristics rely on static penalty schedules that fail on complex congestion topologies, we present AlphaRoute: a multi-objective adaptive search framework reformulating rip-up and reroute (R&R)...
-
39
Convergence-Latency-Aware Adaptive Modulation and Resource Allocation in RIS-Assisted Wireless Federated Learning
Liwei Wang, Wen Chen, Jun Li, Qingqing Wu, Ming Ding, Xusheng Zhu, Qiong Wu
cs.LG · cs.AI · cs.IT
Federated learning (FL) over wireless networks suffers from significant training latency and degraded convergence due to unreliable wireless transmission, especially under blocked propagation environments. Although reconfigurable intelligent surfaces (RISs) can improve communication reliability, existing wireless FL studies rarely characterize the trade-off between learning convergence and communication delay under modulation-dependent...
-
40
The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
Gurp Nijjer
cs.LG · cs.AI
Model-based reinforcement-learning agents of the DreamerV3 family forget catastrophically when trained on task sequences, even when an unbounded replay buffer preserves every earlier experience. We ask a question the continual-RL literature has assumed an answer to but never measured: which component forgets? Under never-clear replay, pre-registered component-level probes (n=3 seeds throughout) show that the world model retains essentially...
-
41
Analytic Distribution of Classifier-Free Guidance for Schedule Design
Enze Jiang, Zheng Ma
cs.LG · cs.CV
Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministic guided dynamics is not captured by the usual product-distribution heuristic $p_0^ωq_0^{1-ω}$. We analyze CFG through the probability flow ODE and derive exact analytic path-integral representations of the induced distributions for both constant and time-dependent guidance. The resulting...
-
42
Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination
Jiaqi Li, Xinglong Zhang, Haibin Xie, Yixing Lan, Wei Pan, Xin Xu
cs.LG · cs.RO
Latent world models improve sample efficiency in continuous control by optimizing policies over imagined latent trajectories, but common neural transitions offer limited direct control over modal persistence and error accumulation in long rollouts. We propose Koopman Dreamer, a Dreamer-style world model with a spectrally constrained deterministic latent dynamics core. Its Koopman-inspired backbone uses two-dimensional rotation--scaling blocks...
-
43
How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF
Venkata Naga Sai Vishnu Rohit Pulipaka, Anish Katta, Deva Rohit Reddy Peddireddy
cs.LG
In RLHF pipelines, reward scoring blocks policy updates. Slow scoring bottlenecks the entire loop, since no update runs until every rollout gets a score. And yet most setups just default to PyTorch eager mode or torch.compile, no one checks if that's actually fastest. Scoring itself is small. Rollout generation eats far more of a typical RLHF step. But scoring and generation fight over the same CPU and GPU resources, so a faster scoring...
-
44
Efficient Clustering with Provable Guardrails for LLM Inference at Scale
Longshaokan Wang, Wai Tsang Keung, Punit Ghodasara, Roman Wang, Ali Dashti, Francesc Moreno-Noguer
cs.LG · stat.ML
Scaling LLM-based applications to millions of users is bottlenecked by the inference cost and latency of modern foundation models. A natural fix is to cluster the inputs and call the LLM only on cluster representatives, letting other members inherit the output -- but this is only safe if each member is measurably close to its representative. Existing clustering methods do not offer such per-sample quality control at scale: none jointly...
-
45
Expert-Guided Forecast Editing for Time-Series Foundation Models
Hung Le, Minh Hoang Nguyen, Manh Nguyen, Huu Hiep Nguyen, Dai Do
cs.LG
Time-series foundation models can forecast across heterogeneous domains without task-specific training, but their forecasts are fixed once produced and cannot directly incorporate task-specific expert feedback. We study expert-guided forecast editing: a frozen foundation model generates candidate future trajectories, and an expensive expert evaluator scores them to guide forecast revision. Under a tight query budget, two natural strategies...
-
46
Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Search Inertness in Clue-Rich Completion
Aleksey Komissarov
cs.LG · cs.AI
Neural solvers are built to deduce, branch, and revise intermediate states. The Lattice Deduction Transformer (LDT) appears to do exactly that. In clue-rich Sudoku, it does not: one forward pass commits essentially the entire grid (every blank cell on standard 6x6, 94-96% on augmented 9x9), turning the iterative solver into a one-shot predictor wrapped in an exact verifier. All hard-slice failures are decided before search begins, when the...
-
47
HypEMBER: Hypernetwork-based Ensemble for Robust Policy Learning of Parametrized Dynamical Systems
Nicolò Botteghi, Gabriele Pascali, Urban Fasel, Andrea Manzoni
cs.LG
In this work we investigate reinforcement learning (RL) as a framework for the robust control of parametrized dynamical systems in presence of measurements and model uncertainties. High-dimensional state spaces, expensive numerical solvers, the partial knowledge of the governing equations, and the dependence on physical parameters that may be uncertain or difficult to estimate accurately, make the use of standard RL approaches computationally...
-
48
SCPP: A Unified Python Library for Soft Clustering
Kiyan Rezaee, Morteza Ziabakhsh, Artin Bahrampour, Seyed Mohammad Ghoreishi, Asal Khaje, Ali Sajedifar, Manny...
cs.LG · cs.AI
In this paper, we present SCPP (Soft Clustering Python Package), an open-source Python framework for soft clustering. SCPP establishes a canonical, scikit-learn-compatible estimator interface that standardizes model training, prediction, membership representation, evaluation, and benchmarking across heterogeneous soft clustering methods, including fuzzy, probabilistic, graph-based, matrix factorization, and deep learning methods. The...
-
49
The Mechanism Matters: When Knowledge Graphs Help Reinforcement Learning
Mohammed Sameer Syed
cs.LG
Knowledge graphs (KGs) are widely used to inject prior knowledge into reinforcement learning (RL), yet the literature is dominated by single-domain, positive-result method papers, so we lack a systematic account of when KG structure helps an agent, when it is neutral, and when it hurts. We conduct a controlled study that independently varies the RL task, the injection mechanism (state features, action masking, or potential-based reward...
-
50
End-to-End Differential Privacy in Training Deep Neural Network Classifiers
Huaiyuan Rao, Calvin Hawkins, Alexander Benvenuti, Matthew Hale
cs.LG · cs.CR
Differentially private machine learning enables model training on sensitive data while ensuring that individual data is unlikely to be recoverable from the parameters of the resulting model. However, existing work often privatizes both training inputs and their labels, and these protections may be conservative when labels are public or can be safely made public. Therefore, in this work we propose a novel private training framework that...
-
51
Agent-Centric Animal Pose Forecasting
Eyrun Eyjolfsdottir, Kristin Branson
cs.LG
Understanding animal behavior at an algorithmic level -- what animals attend to, how they form internal models and plans, and how this maps to action -- remains a central challenge in neuroscience and ethology. Data-driven generative models offer a path toward this understanding. We introduce a framework for training agent-centric autoregressive models of animal behavior from tracked pose, applicable to single animals and to groups in which...
-
52
Trustworthy Privacy-Preserving Multimodal Federated Learning for Personalised Breast Cancer Prediction
Ruth Amey, Muhammad Arifur Rahman, Taha Osman, Nicholas Shopland, Andy Burton, Mufti Mahmud, David J. Brown
cs.LG · cs.AI
Federated learning has emerged as a potential solution to privacy concerns associated with using sensitive health data for training predictive models, particularly in personalised cancer care. This research investigates whether federated learning can support the development of robust models for predicting tumour progression in breast cancer patients while addressing four critical deployment pillars: transparency, scalability, security, and...
-
53
The C-index illusion: discrimination without calibration in published survival models
Rafael da Silva, Danilo Alvares
cs.LG
"Stop Chasing the C-index when Evaluating Survival Analysis Models" (ICML 2026, Spotlight) argued normatively, on synthetic data, that evaluating survival models by discrimination alone, i.e. the concordance index, produces systematically misleading model comparisons, because the metric ignores calibration and time-dependent accuracy. Whether this matters for real, published, non-clinical models has not been tested. We reproduce three...
-
54
SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework
Akarsh K Nair, Muhammad Arifur Rahman, Nicholas Shopland, Andy Burton, Jun He, Yuan Shen, David Baldwin, Emma...
cs.LG · cs.AI · cs.DC
Federated learning (FL) offers a promising approach to privacy-preserving clinical risk prediction, but its deployment remains limited by restricted data sharing, client heterogeneity, class imbalance, and the lack of realistic tabular electronic health record (EHR) benchmarks. Synthetic data generation may alleviate data scarcity, yet its integration with federated optimisation has received limited systematic study. We propose SynPre-FL, a...
-
55
Geospatial Diffusion-based Evolution Synthesis (GeoDES) for Storm-Centered Weather Augmentation
Sonia Cromp, Satya Sai Srinath Namburi GNVV, Youran Wang, Grace Kisslinger, Frederic Sala, James Booth, Allegra LeGrande
cs.LG · cs.CV
While machine learning-based weather models hold significant promise, they struggle to predict the detailed structure of large-scale weather systems such as cyclonic storms. Regional models are constrained by limited historical records within fixed geographic boundaries, while global models are computationally expensive and often operate at resolutions too coarse to capture fine-grained storm dynamics. To bridge this gap, we introduce the...
-
56
Do Sheaf Neural Networks Use Holonomy? A Measure--Intervene--Control Study
Ankit Grover, Rémi Bourgerie
cs.LG
Geometric architectures are often justified by internal mechanisms such as rotations, yet task performance alone cannot show whether those mechanisms drive predictions. Using sheaf neural networks (SNNs) as a testbed, we introduce the first basis-independent measurement of trained triangle-loop products, separating rotation, stalk-space area, and orientation. In a custom high-homophily GraphUniverse regime, Neural Sheaf Propagation (NSP)...
-
57
Total Variation Distance Estimation in Autoregressive Models
Eric Price, Kevin Tian, Zhiyang Xun, Yusong Zhu
cs.LG · cs.DS · stat.ME · stat.ML
Modern LLM deployments use a number of implementation choices and inference optimizations (e.g., batching, custom kernels, and quantization) on top of fixed weights, so two engines serving "the same model" can produce meaningfully different distributions. We study the problem of estimating the total variation (TV) distance between two length-$n$ autoregressive distributions to additive error $\varepsilon$, under three access models. (1) Under...
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.