cs.LG · 2026-09-04 · No. 105

Machine Learning, 2026-09-04.

48 new papers in cs.LG. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

48 entries
  1. 01

    Robust PAC Learning of Concurrent Stochastic Games

    Angel Y. He, David Parker

    cs.LG · cs.GT · cs.LO · cs.MA

    We introduce the first Probably Approximately Correct (PAC) learning framework for general-sum concurrent stochastic games (CSGs) with transition uncertainty, while addressing the challenge of Nash equilibrium (NE) existence. Our algorithm maintains data-driven $L^1$ confidence sets over transition kernels and solves a robust CSG to compute a social-welfare optimal $\varepsilon$-NE, using a robust MDP-based exploration mechanism to drive...

    arxiv.org/abs/2609.04189 · PDF

  2. 02

    A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann Vehicle

    Gustavo Claudio Karl Couto, Eric Aislan Antonelo, Gabriel George Zipperer

    cs.LG · cs.AI · cs.RO

    This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platform combines a physical vehicle, a printed urban track, data collection tools, trajectory registration, and a Webots digital twin, enabling controlled experiments that connect simulation-based autonomous-driving methods to real-world execution. As a first baseline, we implement...

    arxiv.org/abs/2609.04147 · PDF

  3. 03

    Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks

    Shivang Rawat, Mirko Morello, Flaviano Morone, David J. Heeger

    cs.LG · cs.NE · q-bio.NC

    Temporal integration gives continuous-time recurrent networks memory, but in deep stacks it also delays bottom-up signals and attenuates top-down errors. We develop Recursive Quadrature Filters (RQFs), biologically motivated complex-valued temporal filters that are a special case of diagonal state-space models (SSMs), and ask whether this failure mode can be addressed by making each layer's bottom-up input prospective. Starting from an energy...

    arxiv.org/abs/2609.04134 · PDF

  4. 04

    Constant regret in general games via higher-order optimism

    Omar Abbadi, Rida Laraki, Panayotis Mertikopoulos

    cs.LG · cs.GT

    We introduce an uncoupled learning algorithm which, when employed by all players of an arbitrary $N$-player normal form game with up to $K$ actions per player, guarantees $O(N^3\log^2 K)$ individual regret, uniformly over the horizon of play. The proposed algorithm - which we call higher-order optimism with discounting (HOOD) is a variant of optimistic follow-the-regularized-leader (OptFTRL) that combines a discounted $(N+1)$-th order...

    arxiv.org/abs/2609.04113 · PDF

  5. 05

    Hardware-Aware FP4 FlashAttention-4

    Robert Hu

    cs.LG

    Blackwell's 4-bit floating-point (FP4) tensor cores do not automatically make attention faster because softmax conversion and on-chip dependencies dominate once its matrix products shrink. We address this with \emph{Direct-P} for noncausal inference and a causal path that passes the forward quantization directly into backward. Direct-P maps scores directly to FP4 probabilities and reaches up to 2.13$\times$ the bfloat16 (BF16) forward...

    arxiv.org/abs/2609.04105 · PDF

  6. 06

    Conditioning Degenerate Diffusion Models

    Uğur Aydın, Tamer Başar

    cs.LG

    Current conditioned generative models heavily rely on score functions for guidance during training. When the generative model is a diffusion process with a singular diffusion coefficient and the underlying (conditional) densities either do not exist or are not smooth, we use causal optimal transport to define \emph{approximate} loss functions that identify a minimum-entropy control for guidance under minimal assumptions. Our approach relies...

    arxiv.org/abs/2609.04090 · PDF

  7. 07

    Subspace Inference Enables Efficient Active Reward Learning from Preferences

    Yutai Zhou, Erdem Bıyık

    cs.LG · cs.AI · cs.RO

    Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human preferences, making active learning a critical component in synthesizing informative preference queries. However, effective uncertainty quantification required for active learning remains a key challenge for large neural network reward models. In this paper, we introduce PreferenceEKF, a...

    arxiv.org/abs/2609.04066 · PDF

  8. 08

    A location-invariant estimator of extremal quantile treatment effects for heavy-tailed distributions

    Xin Yu, Shuwei Huang, Jicheng Liu, Jielin Tang, Bolin Wang, Yunxiao Zhang, Tian Zhao

    cs.LG · stat.AP · stat.ME

    Quantile treatment effects (QTEs) measure the effect of a treatment on the distribution of an outcome, and their estimation at extreme quantile levels is of central interest in applications where the target quantiles lie far beyond the range of the data. For heavy-tailed potential outcomes, existing extremal QTE estimators rely on extrapolation combined with a causal extreme value index (EVI) estimator, but the resulting estimator is not...

    arxiv.org/abs/2609.04018 · PDF

  9. 09

    Unlocking Lossless Speedups in LLMs via Discrete Diffusion

    Subham Sekhar Sahoo, Lingjie Chen, Khiem Pham, Jonathan Geuter, Chaitanya Dwivedi, Varad Pimpalkhute, Yash Akhauri,...

    cs.LG

    Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential token generation. To overcome this bottleneck, we introduce diffusion-augmented LLMs, a new class of models that defines an AR model distribution while using diffusion to draw multiple tokens in parallel from that distribution. We decouple the parameters of these models into two sets: AR...

    arxiv.org/abs/2609.04010 · PDF

  10. 10

    RobustSeiz: An Open-Source Framework for Benchmarking the Robustness of EEG Seizure Detection Models

    Mohammad Mohammadi, Alireza Zarei

    cs.LG · eess.SP

    Despite strong performance on held-out electroencephalography (EEG) data, seizure detectors may fail under real-world acquisition variability, artifacts, and adversarial inputs. We introduce RobustSeiz, an open-source, model-agnostic framework that provides a standardized, reproducible protocol for stress-testing and comparing seizure detectors under controlled, clinically motivated distribution shifts before deployment. We standardize four...

    arxiv.org/abs/2609.04007 · PDF

  11. 11

    OSR: Output Space Redistribution for Adaptive Label Removal in Classification Models

    Minyi Peng, Darian Gunamardi, Ivan Tjuawinata, Yongsen Zheng, Kwok-Yan Lam

    cs.LG

    Label removal occurs frequently in classification systems with evolving taxonomies, where categories must be dynamically updated or eliminated. To accommodate such changes, classification models must adapt accordingly. Existing solutions, broadly categorized as retraining-based and feature-space-adjustment-based, share common limitations despite their variations, including reliance on access to original data, substantial computational and...

    arxiv.org/abs/2609.03972 · PDF

  12. 12

    VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch

    WenJie Fan

    cs.LG · cs.CL

    The problem. A long-lived KV cache must be compressed before the queries that will read it exist; selection by observed attention (H2O, SnapKV) collapses there (0.00-0.33 needle retrieval on a NoPE MLA model), because a token's importance has not yet been observed. The method. On Kimi Linear, VestigeKV evicts by a query-independent signal the cache already carries: the 64-dimensional decoupled branch, a vestige of RoPE that NoPE training...

    arxiv.org/abs/2609.03949 · PDF

  13. 13

    Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPO

    Hyun Bin Park, Du-Seong Chang

    cs.LG · cs.AI · cs.CL

    RL-based post-training for reasoning models is increasingly bottlenecked by repeated fresh rollout generation, particularly in agentic settings where environment interaction dominates wall-clock cost. Replay can reduce this burden by reusing past trajectories, but existing methods typically embed it within larger training pipelines involving exploration, experience restructuring, or mixed-policy optimization. This makes replay's own...

    arxiv.org/abs/2609.03941 · PDF

  14. 14

    RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting

    Yuchen He, Yueyang Cang, Zhiyuan Ning, Ningyu Wang, Li Shi

    cs.LG · cs.AI

    Retrieval-augmented generation (RAG) complements parametric models with retrieved external evidence. The same idea is attractive for continuous-output regression, but directly reusing retrieved target values is often not robust when samples differ in output level, numerical scale, or local dynamics. Moreover, conventional forecasting pipelines generally use residuals for model optimization and error diagnosis, but do not retain individual...

    arxiv.org/abs/2609.03937 · PDF

  15. 15

    Beyond Endpoint Scores: Time- and Capacity-Conditioned Evaluation of Continual Knowledge Updating

    Heejin Choi

    cs.LG

    Continual knowledge-updating methods are often declared superior from one final checkpoint and one conventional adapter rank. We show that this can be insufficient to identify the better operating point. Holding a periodic hierarchy fixed, we compare it with cumulative replay over a 24-month Wikidata stream while varying evaluation month, replay LoRA rank, and query formulation. The apparent winner changes across this region: on Qwen2.5-1.5B,...

    arxiv.org/abs/2609.03900 · PDF

  16. 16

    Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data

    Lamine Diop, Marc Plantevit

    cs.LG · cs.AI

    Reconstruction-based anomaly detectors are accurate but opaque: a deep autoencoder flags a sample without telling a practitioner which feature ranges made it anomalous. We propose DIFFINT, an autoencoder whose latent bottleneck is structured as a set of soft, axis-aligned interval memberships learned end-to-end directly from raw numerical data, without any discretization or binarization. Each latent unit corresponds to a human-readable...

    arxiv.org/abs/2609.03878 · PDF

  17. 17

    High-Dimensional Learning Dynamics of Attention-Indexed Models

    Yizhou Xu, Margarita Sagitova, Lenka Zdeborová, Florent Krzakala

    cs.LG · stat.ML

    Attention mechanisms are central to modern foundation models, yet their training dynamics remain poorly understood, especially when the attention matrices have extensive rank. In this work, we study attention-indexed models, a broad framework that can represent multi-layer and multi-head attention architectures. First, we show that, in a suitable high-dimensional limit, the population-loss landscape is characterized by a finite set of trace...

    arxiv.org/abs/2609.03858 · PDF

  18. 18

    Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning

    Michael Khavkin, Kichang Lee, Jaeho Jin, JeongGil Ko, Eran Toch

    cs.LG

    Federated Learning (FL) with Differential Privacy (DP) is increasingly adopted to preserve data confidentiality in distributed machine learning. However, DP noise distorts learned representations and degrades explanation fidelity, limiting differentially private FL where trustworthy explanations are required, such as assistive clinical diagnosis. Prior work adapted DP noise with static feature-importance signals, restricting explainability to...

    arxiv.org/abs/2609.03851 · PDF

  19. 19

    Multi-step Proximal Policy Improvement in Offline Reinforcement Learning

    Soohyun Choi, Seonvin Cho, Songnam Hong

    cs.LG

    Offline reinforcement learning (RL) must reconcile two competing requirements: policy updates should stay near dataset-supported actions to keep value estimates reliable, yet meaningful gains often require moving beyond the behavior distribution. We develop a geometric view of offline actor updates by modeling policies as a probability manifold endowed with a chosen metric geometry. Under this lens, a broad class of offline actor objectives...

    arxiv.org/abs/2609.03842 · PDF

  20. 20

    Witnesses Explain Anomalies

    Lamine Diop

    cs.LG · cs.AI

    Unsupervised anomaly detection scores each point of an unlabelled, contaminated sample in a single pass, and increasingly must also explain why a point is flagged. Yet the dominant detectors give a score with no account of which features drive it, and explanations are bolted on post-hoc with SHAP or LIME, which re-query the detector thousands of times per point and only approximate it. We introduce WAND, an unsupervised tabular anomaly...

    arxiv.org/abs/2609.03826 · PDF

  21. 21

    A Peer-Relative Representation Learning Framework for Energy Inefficiency Identification in Mobile Network Sites

    Eliud Nyakweba Koto, Jaco du Toit, Adham Stoltz, Johan du Preez

    cs.LG

    Energy consumption is one of the largest operational expenditure items for mobile network operators, yet site-level energy inefficiencies such as faulty cooling controllers, idle radio equipment, and parasitic auxiliary loads often remain undetected because no ground-truth inefficiency labels exist and historical measurements may already contain embedded inefficiencies. This study proposes an unsupervised peer-relative approach based on the...

    arxiv.org/abs/2609.03809 · PDF

  22. 22

    Free Pause Tokens

    John Langford, Nathan Godey, Giovanni Monea, Yoav Artzi, Harry Dong, Ying Fan, Gustavo de Rosa, Zheng Zhan

    cs.LG · cs.AI

    A free pause token gives a language model extra compute to form each next-token prediction (as a pause, or thinking, token does) but carries that compute in a parallel prediction stream over a weight-shared backbone rather than as an extra token in the sequence. It improves next-token prediction by 2-3 centinats in practice on a 1B parameter model. Because the pause rides an existing position instead of adding one, it is free to use: at...

    arxiv.org/abs/2609.03807 · PDF

  23. 23

    From Ordered Bernoulli Levels to Critical-Line Geometry: Integer Quantization, Bernoulli Residual Phase, and Prime-Power Spectra

    Y. Kenan Yılmaz

    cs.LG · math.NT

    We study the ordered Bernoulli-word kernel f(p,n,k)=p^k(1-p)^(n-k) and the geometry generated by its inverse-integer level sets. The binary level 2^(-n) selects p=1/2 as the unique real split-independent anchor. Under complement-preserving complex continuation, the pair becomes z=1/2+iu and 1-z=1/2-iu, producing a conjugation-symmetric vertical geometry before any zeta-function input is introduced. The quadratic coordinate Q(z)=z(1-z)=1/4+u^2...

    arxiv.org/abs/2609.03801 · PDF

  24. 24

    Landmark-Based Discrimination of Injury-Associated Athlete-Sessions from Minute-Resolution Multimodal Football Monitoring Data

    Evangelos Chatzidimitriou, Konstantinos Tserpes

    cs.LG

    Athlete monitoring data may be recorded minute by minute throughout a match or training session, while injury information may only indicate whether the entire session was injury-associated. This creates a modelling problem: assigning the same session-level label to every minute would imply that injury status is known at each exact time, even though within-session injury onset is unknown. Our novelty is a fixed-landmark,...

    arxiv.org/abs/2609.03790 · PDF

  25. 25

    OBER+: Continuity-Aware Reporting and Traceable Continuous Improvement in Outcome-Based Education

    Elakkiya Rajasekar

    cs.LG · cs.CL · cs.CY

    Institutions practising outcome-based education compute learning outcome attainment routinely, while reviews of curriculum analytics report an absence of evidence on how that computation informs decisions. This paper presents OBER+, an extension of a deployed institutional attainment platform that computes the step from a measured shortfall to an evaluated corrective action. Five connected stages accumulate attainment across deliveries of a...

    arxiv.org/abs/2609.03770 · PDF

  26. 26

    From Nowcasting to Forecasting: Adapting a Reanalysis-Trained

    Mikko Partio, Leila Hieta, Ossi Laine

    cs.LG · physics.ao-ph

    Accurate cloud-cover forecasts are important for temperature prediction, radiation forecasting, and solar-power operations. Short-range forecasting methods can preserve observed cloud placement during the first forecast hours, but their skill decreases when cloud fields evolve through formation, dissipation and deformation. Longer lead times require accounting for atmospheric evolution, but operational numerical weather prediction (NWP)...

    arxiv.org/abs/2609.03763 · PDF

  27. 27

    Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step Size

    A. Afham

    cs.LG · math.OC · quant-ph

    The computation of the Bures-Wasserstein (BW) barycenter of an ensemble of positive definite matrices arises throughout machine learning, optimal transport, and quantum information. Riemannian gradient descent (RGD) at unit step size -- the fixed-point iteration used in practice -- converges rapidly, yet existing analyses present a dichotomy: unit-step guarantees carry worst-case exponential dependence on the dimension, while...

    arxiv.org/abs/2609.03762 · PDF

  28. 28

    Federated Causal Discovery via Regression-Directed Cumulants

    Pablo Torrijos, Fabio Stella, José A. Gámez, José M. Puerta

    cs.LG

    In this paper we study linear non-Gaussian acyclic models (LiNGAM) when used in federated environments. These causal models allow one to go beyond Markov equivalence. However, in many domains data are scarce, and increasing the sample size by centralising data from different clients is not advisable due to regulations such as the GDPR. The federated environment offers an attractive option to balance privacy and causal discovery accuracy....

    arxiv.org/abs/2609.03705 · PDF

  29. 29

    Resolution-Aware Experimental Design under Partial Identifiability

    Sofianos Panagiotis Fotias

    cs.LG

    Experimental design is commonly framed as choosing the experiment expected to provide the most information. Under partial identifiability however, persistent nuisance uncertainty can make the same observation carry different structural meanings. We introduce Resolution-Aware Experimental Design (RAED), which selects an experiment by the smallest expected nonempty structural candidate set achievable subject to false-exclusion control. We prove...

    arxiv.org/abs/2609.03686 · PDF

  30. 30

    Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning

    Oussama Hidaoui, Omer Ebead, Ulrich Armel Mbou Sob, Siddarth Singh, Juan Claude Formanek, Felix Chalumeau, Omayma...

    cs.LG · cs.AI

    Generalising to unseen tasks remains a fundamental challenge in offline multi-agent reinforcement learning (MARL). In this work, we present a principled analysis of zero-shot task generalisation in the offline setting and conduct an extensive empirical investigation into the scaling behaviour governing task diversity, dataset size, and network capacity. To facilitate this study, we extend offline sequence modelling architectures to handle...

    arxiv.org/abs/2609.03667 · PDF

  31. 31

    Extracting Forgotten Prompts from Targeted Unlearned Models

    Au Ashley Hoi-Ting, Meghdad Kurmanji, William F. Shen, Nicholas D. Lane, Ligang He

    cs.LG

    Recent unlearning methods (e.g. NPO, DPO, LUNAR) make use of refusal alignment to suppress forgotten data. However, it has been shown that refusal responses might leave traces of unlearning, and recent attacks have been able to successfully recover some of the unlearned knowledge. In this paper, we uncover a new vulnerability. Existing attacks typically assume that the forgotten prompts are already known to the adversary and focus on...

    arxiv.org/abs/2609.03662 · PDF

  32. 32

    Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners

    David Milec, Spyridon Samothrakis, Michael Fairbank, Dennis J. N. J. Soemers

    cs.LG · cs.AI

    The dominance of Neural Networks (NNs) in RL is partially due to their incremental learning capability, which naturally suits the online, non-stationary nature of self-play training. However, gradient-boosted trees like LightGBM are widely recognised as the state of the art for tabular data in supervised learning, often outperforming NNs in accuracy and efficiency. Game states are inherently tabular---discrete actions, categorical card...

    arxiv.org/abs/2609.03660 · PDF

  33. 33

    On the Interaction Between Model Compression and Test-Time Adaptation

    Francesco Corti, Dong Wang, Young D. Kwon, Cecilia Mascolo, Olga Saukh

    cs.LG · cs.AI

    Deep neural networks deployed in the wild must be both efficient and adaptable, requiring model compression and test-time adaptation (TTA). While both are well studied in isolation, their interaction remains poorly understood. We systematically analyze how structured compression affects a model's ability to adapt under distribution shift. Using ResNet-18 and ViT-Base on CIFAR-10-C and ImageNet-C, we evaluate multiple compression methods...

    arxiv.org/abs/2609.03604 · PDF

  34. 34

    Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling

    Alessandro Grassi, Edoardo Kimani Bellotto, Wassim El Azami, Sabrina Outmani, Maximilien Houel

    cs.LG · eess.IV · physics.data-an · q-bio.PE

    Species Distribution Modelling (SDM) is essential for understanding how environmental conditions shape biodiversity, particularly for destructive pests such as the Desert Locust (Schistocerca gregaria), whose breeding dynamics are tightly coupled to rapidly evolving environmental conditions. Maxent has become the dominant method for presence-only data, but its reliance on a linear combination of hand chosen feature transforms limits its...

    arxiv.org/abs/2609.03603 · PDF

  35. 35

    WeatherNext 3: Increasing resolution and performance of global weather models with raw observations

    Stephan Rasp, Boris Babenko, Dominic Masters, Andrew El-Kadi, Samier Merchant, Guy Shalev, Ilan Price, Fred Zyda,...

    cs.LG

    State-of-the-art AI weather models have shown impressive medium-range forecast skill and computational efficiency, but suffer two key shortcomings: their forecasts have lower spatial and temporal resolution than the best physics-based models and they are exclusively initialized with and trained on analysis data. As a result, they cannot directly make use of observations, and any biases in the analysis are inherited by the forecast....

    arxiv.org/abs/2609.03582 · PDF

  36. 36

    Coupled Scaling: A Representational Accessibility Framework for Neural Scaling Laws

    Jie Wang

    cs.LG

    Existing theories derive neural scaling from data geometry or a specified data-model spectrum, but systems trained on the same data can scale differently when architecture or optimization changes the representations they can efficiently reach. We introduce Coupled Scaling, a task-conditioned framework in which finite-budget scaling depends on the relation between task structure and the geometry accessible to an architecture-optimization...

    arxiv.org/abs/2609.03533 · PDF

  37. 37

    LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL

    Sijie Wang, Zhiqiang Tan, Xinrui Yang, Shaohuai Shi

    cs.LG · cs.AI · cs.AR

    Diffusion reinforcement learning (RL) has recently achieved significant success in post-training image and video generative models. However, most diffusion RL methods, including DanceGRPO and FlowGRPO, recompute selected timesteps with gradient tracking after rollout. Under on-policy training with the same backend for rollout and update, this recomputation is mathematically redundant. Intuitively, the rollout and policy update steps can reuse...

    arxiv.org/abs/2609.03528 · PDF

  38. 38

    LongCounsel-8: A Benchmark Suite for Longitudinal Depression Tracking from Multi-Session Counseling Dialogues

    Jiayi Li, Zhaomin Wu, Bingsheng He

    cs.LG · cs.AI

    Tracking depression from multi-session counseling dialogues requires estimating both current symptom severity and how it changes across sessions. Yet progress on this task is constrained by the scarcity of longitudinal counseling data with standardized session-level depression labels. Existing resources typically provide either multi-session conversations without depression labels or labeled interviews in a single session. Building such a...

    arxiv.org/abs/2609.03507 · PDF

  39. 39

    An Adversarial Zero-Shot Learning Approach for Anomaly Detection in Multivariate IoT Traffic Data

    Mahshid Rezakhani, Tolunay Seyfi, Fatemeh Afghah

    cs.LG · cs.NI

    Anomaly detection in Internet of Things (IoT) networks presents unique challenges due to the diversity of devices, lack of labeled data, and domain variability across environments. In this paper, we propose a novel framework for multivariate time-series anomaly detection that leverages adversarial learning and contrastive loss within a sequence-based Variational Autoencoder (VAE) architecture. Our method enables zero-shot domain adaptation by...

    arxiv.org/abs/2609.03505 · PDF

  40. 40

    Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails

    Shi Fu, Huibo Xu, Qixin Zhang, Dacheng Tao

    cs.LG

    Restricted eigenvalue (RE) bounds govern stable recovery by norm-regularized estimators. For isotropic sub-Gaussian measurements, the benchmark sample size is $1+w(A)^2$, where $w(A)$ is the Gaussian width of the normalized descent cone. The COLT 2015 open-problem note (Banerjee et al., 2015) asked whether the same law follows for heavy-tailed designs from a uniform small-ball condition alone. We give an explicit and systematic negative...

    arxiv.org/abs/2609.03504 · PDF

  41. 41

    Spectral characteristics of autoencoder parameters as a vector representation of data

    Maria Nikitina, Anton Bishuk, Oleg Bakhteev

    cs.LG · stat.ML

    This paper examines the relationship between the parameters of autoencoder models and the statistical properties of the data on which they are trained. Autoencoders are defined as models with an encoder-decoder architecture, trained to reconstruct input data through a compressed latent representation. It is proposed that the model parameters can be viewed as a dense vector representation of the corresponding sample. To test this hypothesis, a...

    arxiv.org/abs/2609.03495 · PDF

  42. 42

    Mind the Gap: Robustness Risks in PII Detection Systems

    Adeel Zafar, Slawomir Nowaczyk

    cs.LG

    Personally Identifiable Information (PII) detection is a foundational component of data protection infrastructure where missed entities constitute direct privacy and security risks. Although modern PII systems report strong performance on standard benchmarks, we show that these evaluations mask substantial robustness failures under realistic distribution shifts encountered in deployment. Rather than comparing state-of-the-art accuracy, we...

    arxiv.org/abs/2609.03464 · PDF

  43. 43

    A Two-Stage Forecasting System for CPU Workload Prediction in Private Clouds

    Ashir Javeed, Anton Borg, Håkan Grahn, Lars Lundberg, Dhyey Patel, Sogand Shirinbab

    cs.LG

    Accurate cloud resource forecasting is essential for proactive resource provisioning, maintaining Quality of Service (QoS), and reducing operational costs in dynamic cloud environments. The existing forecasting approaches predominantly estimate future CPU workload directly from historical resource traces, which often overlook the relationship between customer service demand and subsequent resource consumption. This study proposes a two-stage...

    arxiv.org/abs/2609.03457 · PDF

  44. 44

    Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling

    Junyi Lin, Mengyu Li, Jingxuan Hu, Kejun He, Cheng Meng

    cs.LG

    The performance of Flow Matching largely depends on the quality of the coupling between the source and target distributions. However, independent coupling often leads to path crossings and local velocity ambiguity, while OT-based couplings typically incur high construction costs. To address this challenge, we propose Quantile AlignTree Flow Matching (QAT-FM), an efficient structured coupling strategy that constructs a hierarchical coupling...

    arxiv.org/abs/2609.03443 · PDF

  45. 45

    Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal Discovery

    Sairam Sundararaman, Sara Girdhar, Manit Narasimha Murthy, Samrudh N, Bhaskarjyoti Das

    cs.LG

    Differentiable causal discovery methods increasingly encode expert priors as forbidden-edge constraints enforced by an Augmented Lagrangian (ALM) penalty, on the assumption that a data-adaptive relaxation mechanism will discount and eventually override a rule the data consistently contradicts. We show this design, which we call \emph{guide, not bind}, fails for two independent, precisely characterized reasons, and that directly repairing both...

    arxiv.org/abs/2609.03442 · PDF

  46. 46

    It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories

    Yigit Utku Bulut

    cs.LG · cs.AI · cs.CL

    Reasoning traces of large language models are widely read as containing "breakthrough" moments and early-legible fates. Both readings rest on measurements missing a counterfactual control at the level of the claim; we supply both controls. First, a restart-controlled truncation probe separates when a solution fits the continuation budget from when a prefix carries value that fresh computation cannot buy, comparing per-anchor continuation...

    arxiv.org/abs/2609.03436 · PDF

  47. 47

    TraveL: Transformer-based Multi-view Path Distributional Representation Learning

    Fang He, Tao-yang Fu, Wang-chien Lee

    cs.LG · cs.AI

    Path representation learning (PRL) for road networks has received increasing research attention, due to various path-related applications. Existing works on PRL typically exploit the co-occurrence relationship among road segments and paths to learn a vector as the path representation, without exploring the varied traveler behaviors and the regional correlation on the path. In this work, we propose to learn distributional representations,...

    arxiv.org/abs/2609.03427 · PDF

  48. 48

    Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models

    Ross Tieman, Evan Markou

    cs.LG · cs.MA

    Diversity is a widely observed factor in the resilient function of collective systems, yet the type of diversity that matters depends on the properties and failure modes of the system. This distinction is important for systems composed of multiple language models. Different models may be treated as independent components even when their behaviour and failures remain strongly correlated. Assessments of language-model populations using semantic...

    arxiv.org/abs/2609.03422 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.