cs.LG · 2026-08-23 · No. 93
Machine Learning, 2026-08-23.
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
A comparison between ceiling-mounted FMCW, IR-UWB and Wi-Fi radar for in-bedroom human activity monitoring and sleep interruption detection
Anton Lambrecht, Reda El Hail, Xianjun Jiao, Pieter Crombez, Dominique Schreurs, Peter Karsmakers, Adnan Shahid, Eli...
cs.LG
Despite their growing importance for contact-free radio frequency (RF) based healthcare monitoring, different radio technologies such as frequency-modulated continuous wave (FMCW) radar, impulse radio ultra-wideband (IR-UWB), and Wi-Fi sensing are rarely compared under identical deployment conditions, as existing studies typically differ in hardware, datasets, and evaluation methodologies. In addition, the performance of ceiling-mounted...
-
02
Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records
Jun Ni Du, Lukas Adamek, Maxim Kryukov, Flavio Dormont, Ziv Bar-Joseph, Sven Jager, Brandon Rufino
cs.LG
Predictive models over structured electronic health records (EHRs) remain central to machine learning for healthcare, but few have jointly emphasized quantitative laboratory information and interpretability with respect to input medical events. We present BERT-LER, a BERT-style model for coded EHR timelines pretrained and fine-tuned from a de-identified EHR dataset of 75 million patients, that encodes laboratory test results as discrete...
-
03
Physical-Support Confidence Sets for Highly Coherent Dictionaries
Guan-Ju Peng
cs.LG · eess.SP · math.ST
Sparse pursuit after dictionary learning can yield a precise atom support even when its physical interpretation is not justified by the calibration data, especially for highly coherent dictionaries where alternative calibration-compatible dictionaries may assign different physical meanings to the same selected support. We develop resolution-aware physical-support inference that jointly accounts for uncertainty in the learned dictionary and in...
-
04
Dynamic Structural Causal Modeling for Sleep
Ranveer Singh, Saurabh Mathur, Pranuthi Tenali, Arun Badi, Sriraam Natarajan
cs.LG
The causal dynamics of sleep-disordered breathing are complex and vary across patient populations, hindering the development of targeted interventions. We learn dynamic causal graphs of sleep-disordered breathing from Home Sleep Apnea Test (HSAT) recordings, revealing systematic differences in causal structure across sex and age subcohorts. We do so using the PCMCI+ algorithm on windowed fractional variables derived from 105 HSAT recordings,...
-
05
DICS: Data-Informed Centroid Splitting for Decision Tree Classifiers
MD Saifur Rahman Mazumder, Feng Yu
cs.LG · stat.ML
Decision tree-based models are widely used in machine learning due to their interpretability and strong empirical performance. However, training decision trees can be computationally expensive, particularly for large and high-dimensional datasets, largely due to the exhaustive search over candidate splits at each node. To improve computational efficiency, we propose Data-Informed Centroid Splitting (DICS), a clustering-based framework that...
-
06
Decoding silent reading from non-invasive EEG
Ingo Marquardt, Anthilia Alchanat, Priyanka Jain
cs.LG · q-bio.NC
Non-invasive decoding of inner speech faces a fundamental data problem: a corpus pairing brain activity with a person's spontaneous inner monologue cannot be collected, and the available proxy paradigms (cued repetitive and retrospectively reported generative inner speech) are slow to acquire, poorly time-locked, and subject compliance is unverifiable. We therefore treat silent reading as a scalable proxy task and ask how much lexical and...
-
07
Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models
Grégoire Sergeant-Perthuis, Elias Tsigaridas, Jules Tsukahara
cs.LG · cs.SC · math.AG · stat.ML
Classical information criteria such as the Bayesian Information Criterion (BIC) rely on regularity assumptions that break down for singular models, leading to incorrect model selection in settings such as deep learning. The Widely Applicable Bayesian Information Criterion (WBIC) relies on local learning coefficients $λ$, which in the analytic case coincides with local Real Log Canonical Thresholds (RLCT) of the Kullback-Leibler divergence of...
-
08
A Standardized Framework for Machine Learning in Power System Protection
Julian Oelhaf, Georg Kordowich, Paula Andrea Pérez-Toro, Christian Bergler, Johann Jäger, Andreas Maier, Siming Bayer
cs.LG · cs.AI · eess.SP
Studies of machine-learning-based power-system protection increasingly report near-perfect scores, yet the meaning of those scores depends strongly on the evaluation setting. Protection task, physical scope, measurements, timing, targets, preprocessing, and validation often vary jointly and remain incompletely specified. This paper proposes a standardization-oriented framework that treats evaluation design as part of the scientific...
-
09
Ask Self, Ask Others: Relation Is All You Need
Yuting Ge, Pengju Yang, Mingkai Nie
cs.LG
Attention directly derives normalized information flow from pairwise scores. We introduce Relation, an alternative token-mixing primitive that first organizes pairwise evidence into explicit Self and Exchange relations and derives information flow afterward. This relational organization gives rise to Full Relation, FlashRelation, Linear Relation, Hybrid Relation, and a KV-style Relation Cache. Across matched decoder-only models at...
-
10
SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events
Hugo Porta, Emanuele Dalsasso, Chang Xu, Theo Gnassounou, Devis Tuia
cs.LG
The emergence of large-scale Weather and Climate (W&C) datasets offers new opportunities for modeling extreme Earth events (ExEE) and their impacts using deep learning. However, their adoption in operational settings remains limited by the lack of models' interpretability. While for conventional text and image modalities, tools such as Sparse Autoencoders (SAEs) have proven effective for extracting human-understandable concepts, their use for...
-
11
Orthogonal JEPA: Factorized Predictive States for Latent World Models
Taoyong Cui, Pheng Ann Heng, Wanli Ouyang
cs.LG
World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a direct way to learn such states by predicting targets in representation space instead of reconstructing every detail of the observation. Standard JEPAs, however, organize all predictable content through one target embedding and one prediction pathway. In complex systems,...
-
12
Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
Nayeon Kim, Hojin Lee, Yunju Bak, Jaesun Park, Boseop Kim
cs.LG · cs.AI · cs.CL
Mixture-of-Experts (MoE) architectures significantly expand model capacity without a proportional increase in computational cost. However, optimizing their hyperparameters---particularly the learning rate---at extreme scales of both model size and token budget via sweeping remains computationally prohibitive. In this paper, we propose a compute-efficient, two-step hyperparameter transfer framework that estimates optimal learning rates for...
-
13
DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting
Alexander Marusov, Dmitry Anikin, Alexey Zaytsev
cs.LG
Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches. Existing methods often fail to capture the unique inner properties of these components, lack interpretability, or suffer from heavy memory and runtime overhead. To address these limitations, we propose DecoVAE, a lightweight interpretable trend-seasonal VAE framework that explicitly...
-
14
End-to-end Early Classification of Time Series in Non-Stationary Environments
Aurélien Renault, Alexis Bondu, Antoine Cornuéjols, Vincent Lemaire
cs.LG
Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments. Yet, most existing methods assume stationarity and rely on separable designs, where classification and triggering are optimized independently, an assumption that fundamentally limits their adaptability under drift. In this work, we challenge this paradigm and study ECTS under non-stationary...
-
15
An Inclusive and Lightweight Approach to Federated Continual Learning for Cultural Heritage
Ioannis Theologitis, Debin Meng, Stylianos Eleftheriadis, Vasileios Lolis, Konstantinos Votis
cs.LG · cs.AI · cs.CV
Artificial intelligence can support cultural heritage and digital humanities through large-scale retrieval and analysis of digitized collections. However, cultural heritage data are often distributed across institutions, constrained by ownership and access restrictions, and continuously evolving over time. Federated Continual Learning (FCL) is well suited to this setting, as it enables models to learn from distributed and sequential data...
-
16
CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting
Alexander Marusov, Dmitry Anikin, Petr Sokerin, Vitaliy Pozdnyakov, Ilya Kuleshov, Alexey Zaytsev
cs.LG
Probabilistic forecasting models are widely used for time series forecasting in domains such as energy systems, finance, medicine, and transportation. In recent years, deep generative models have shown strong results on probabilistic forecasting, yet many conventional approaches struggle to capture internal temporal dependencies, leading to latent representations with limited expressive power. To address this limitation, we propose...
-
17
Systematic Evaluation of TabPFN-TS for Zero-Shot Probabilistic Heat Load Forecasting in District Heating Networks
Ben Spoek, Karim K. Ben Hicham, Kai Derzsi, Philipp Althaus, Alexander Mitsos, Dirk Müller
cs.LG
District heating energy hubs require reliable heat load forecasts for efficient operational scheduling. Conventional forecasting workflows train system-specific models on historical data, which can become burdensome when networks change through new consumers, retrofits, or changing operating regimes. Zero-shot time-series foundation models and in-context forecasting offer a promising alternative: they can adapt at inference time from recent...
-
18
Scale-Aware Pretraining of Time Series Foundation Models via Multi-Patch Token Alignment and Hybrid Masking
Taihua Chen, Xiang Ma, Yixin Zhang, Tailin Zhan, Manyu Sun, Lizhen Cui
cs.LG
Pretraining time series foundation models across heterogeneous datasets necessitates effective handling of varying sampling frequencies. Current methods either employ dataset-specific patch sizes and separate FFNs, leading to fragmented representations, or enforce a fixed patch size that neglects inherent temporal variations. To address this, we propose SATS, featuring a scale-aware token alignment mechanism that treats patch size as an...
-
19
Green BOA: Determining the environmental break-even point for ML-based data compression
Caterina Doglioni, Akshat Gupta, Thomas Elliott, Hanzila Hussain, Sanjiban Sengupta
cs.LG · hep-ex · physics.comp-ph
We summarise the outcome of two summer internship projects based at the University of Manchester, focused on the break-even point in terms of environmental sustainability for ML-based data compression algorithms. Using the example of a ML-based lossless compression algorithm, we compare estimates for the carbon-equivalent of the infrastructure needed for ML training and inference with the carbon-equivalent savings from reduced disk storage...
-
20
G-MARK: Grounded Multi-Agent Reasoning for Cooperative Driving via Knowledge Graphs
Bhavya Gupta, Onat Gungor, Tajana Rosing
cs.LG
Autonomous driving systems must operate under partial observability, where safety-critical objects may be occluded or visible only to neighboring connected vehicles. Vehicle-to-vehicle cooperation can reduce this uncertainty, but existing cooperative driving methods often compress multi-agent evidence into latent features or hidden multimodal states. As a result, they obscure which agent observed each object, whether the object is visible to...
-
21
Auditing Recorded Predictive Lead Service-Line Classifications Against Physical Verification: A Statewide Study of New York
Muhammad Sarmad Sohail
cs.LG · cs.CY
Under the US Lead and Copper Rule Revisions, a utility may determine a service line's material with a predictive model instead of inspecting it. New York State publishes, per address, which method was used. Almost no address carries both a model classification and a physical verification, so the check is between populations within a utility rather than paired addresses. We screen all 153 New York localities that classified at least 100...
-
22
Multi-Source Wasserstein Distributionally Robust Graph Learning
Chuansen Peng, Yifan Xia, Jinshan Zhong, Xiaojing Shen
cs.LG
Network topology inference from graph signals is central to graph signal processing with applications in neuroscience, sensor, and social networks. In practice, target-domain samples are scarce while heterogeneous source-domain data are abundant. Fusing these sources is challenging: Euclidean averaging works for homogeneous sources but degrades sharply as inter-source divergence grows, collapsing distinct geometries into an inflated, biased...
-
23
PETA:Parameter-Efficient Test-Time Adaptation for Virtual Screening
Jia-Qi Lin, Yinghua Yao, Chang-Dong Wang, Yew-Soon Ong, Yuangang Pan
cs.LG
Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening. DrugCLIP and its recent extensions substantially accelerate this process by encoding protein pockets and molecules into a shared embedding space. Despite this progress, further performance improvements typically require retraining the entire model, incurring substantial computational overhead and...
-
24
Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation
Jia-Qi Lin, Yuangang Pan, Chang-Dong Wang, Haizhang Zhang, Ivor W. Tsang, Joey Tianyi Zhou
cs.LG
Test-Time Adaptation (TTA) methods aim to bridge the domain gap between the source and target domains. However, traditional TTA methods become ineffective when the label distribution shift occurs, a challenge commonly referred to as an open-world scenario. In this paper, we introduce a new method named Reliable Neural Collapse approximation (ReNC) for Open-World Test-Time Adaptation (OWTTA). Specifically, we leverage neural collapse as a...
-
25
Evidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools
Kentaro Oda
cs.LG · cs.AI · cs.NE
Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one, or defer. We present a decision layer that makes all three outcomes statistically meaningful. Reuse and spawn are posed as one-sided sequential hypotheses on a conditional (mechanism-level) discrepancy, separated by an indifference zone; defer is exactly the state in which neither betting...
-
26
Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition
Kentaro Oda
cs.LG · cs.AI
Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one, or defer. We present a decision layer that makes all three outcomes statistically meaningful. Reuse and spawn are posed as one-sided sequential hypotheses on a conditional (mechanism-level) discrepancy, separated by an indifference zone; defer is exactly the state in which neither betting...
-
27
Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection
Jialun Zheng, Hanchen Yang, Jiannong Cao, Yankai Chen, Yuanjing Feng, Philip S. Yu
cs.LG
Generalizable dynamic graph anomaly detection (DGAD) enables pretrained detectors to identify anomalies in unseen target domains without costly retraining. However, existing methods often fail for two reasons. First, they mainly rely on domain-agnostic patterns and miss domain-specific patterns that keep evolving. Second, they assume access to the full target domain data, whereas in more practical online test-time adaptation settings, target...
-
28
Inadvertent Context Leakage in Language Models
Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri, Sanjam Garg, Saeed Mahloujifar
cs.LG · cs.CR
For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data. We study whether the mere presence of such secrets in a model's context window introduces hidden correlations into the model's benign outputs, allowing reconstruction even when the model correctly refuses direct extraction. We further study whether an adversary can actively engineer prompts...
-
29
Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning
Astrid Horn Brorholt, Maris F. L. Galesloot, Nils Jansen, Kim Guldstrand Larsen, Christian Schilling
cs.LG · cs.AI · cs.LO
Probabilistic shielding is a technique for safe reinforcement learning (RL). Typically, a static observer -- called the shield -- constrains the learning agent's actions to those for which acting safely remains feasible. Traditionally, the shield is computed from the transition probabilities of the underlying Markov decision process (MDP). Thus, this technique is not applicable when the MDP model is not given a priori, which, unfortunately,...
-
30
FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide Design
Guofeng Zhang, Rong Han, Xiaoyu Wang, Zhiyun Li, Zongbo Han, Xiaohong Liu, Guangyu Wang
cs.LG
Cyclic peptides are emerging as promising molecular scaffolds in drug discovery due to their high binding affinity and structural stability. However, extending generative models from linear to cyclic peptide design remains challenging, as cyclization sharply restricts the feasible design space through coupled geometric and biophysical constraints. Moreover, limited training data has led existing approaches to rely largely on zero-shot...
-
31
Answer-Level Trust Selection for Physical Vision-Language Reasoning
Rongyu Yu, Ke Niu, Fengxiang He
cs.LG
Vision-language models (VLMs) can estimate physical quantities such as duration, speed, and acceleration from visual observations, but existing benchmarks primarily assess overall model performance against annotated ground truth. In deployment, a key question is whether an individual prediction can be trusted when its ground truth is unavailable. Self-consistency alone may fail to capture important failure modes: a VLM may produce...
-
32
MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents
Bo Qian, Yuting Wu, Shuang Zeng, Huaiyu Wan, Dalin Zhang, Jiqiang Liu
cs.LG · cs.AI · cs.CL
Credit assignment is challenging in long-horizon agentic reinforcement learning, where supervision often comes only from final rewards. Existing methods refine trajectory-level signals into step-level credits through step grouping or graph-based advantage estimation, but can overlook meaningful intermediate milestones. We propose MileGPO (Milestone Inference with Local Evidence for Graph-Based Policy Optimization), which derives process-level...
-
33
Unsupervised Anomaly Detection Using Flow Matching on Tabular Data
Philip Konz, Tejaswini Medi, Margret Keuper
cs.LG
Financial anomaly detection often relies on large unlabeled transaction logs, where anomalous samples may already be present during training. Such training-set contamination violates the clean-normal data assumption underlying many anomaly detection methods. Although flow matching has demonstrated strong performance in generative modeling, its robustness in unsupervised tabular anomaly detection remains underexplored. In this work, we study...
-
34
Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW
Kang Liu, Suyan Li
cs.LG · cs.AI · math.OC · stat.ML
A minibatch can influence training beyond the update at which it is observed because AdamW stores past gradient information in its optimizer states. We study this delayed effect through paired trajectories that differ only in one gradient update and share the same subsequent training sequence. We formulate AdamW as a finite-horizon input--state--output (ISO) system whose state contains the model parameters and first- and second-moment...
-
35
Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay
Haiyue Zhang
cs.LG · cs.AI · cs.CL
Audited against causal ground truth from executed replay in a single-agent tool environment (ALFWorld), none of the step-level credit signals used to train LLM agents -- LLM-judge scores, outcome-conditioned logprob ratios, or the policy's own confidence -- identifies which steps causally matter better than chance. Existing evaluations grade these signals against annotated step *correctness*; we audit them against step *contribution* -- what...
-
36
Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification
Yarin Bar, Yaniv Romano
cs.LG · cs.AI · cs.CL
Inference-time selection methods, such as Best-of-N, improve generation by sampling a pool of candidates and selecting the top-ranked completion according to a reward model. Distillation seeks to amortize this procedure into a single policy by replacing raw rewards with in-pool ranks and learning a policy that upweights higher-ranked completions. However, existing rank-based policies typically use smooth full-support reweighting, so...
-
37
RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations
En Zhi Tan, Jia Xiang Lim, Bryan Lijie Chew, Tze Minh Ng, Benjamin Yan Han Yap
cs.LG
We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic clickstream environments sampled from a broad structural causal prior, enabling it to amortize Bayesian-style inference from a small support set. At inference, a lightweight decoder-only transformer conditions on a handful of domain sequences and produces next-item predictions for queries in a...
-
38
A Locally Tokenized Generative Model for Robust Time-Series Watermarking
Dongbin Kim, Geonwoo Shin, Yujin Choi, Soyeon Park, Jaewook Lee
cs.LG · cs.AI
Watermarking is a central tool for provenance in generative models, yet its application to multivariate time series remains hindered by reliability failures under post-editing attacks. We show that existing detectors, which rely on globally coupled re-encoding, suffer from bidirectional drift of the null distribution: post-editing attacks can shift the z-score of non-watermarked samples in either direction, invalidating clean-calibrated...
-
39
SAGE-XGBoost: Spatially Augmented Graph Embeddings--Machine Learning Framework for Natural Hazards Susceptibility Mapping under Data Scarcity
Mohammad H. Vahidnia, Ali Pourkarimi
cs.LG
Natural hazard susceptibility mapping is often constrained by limited labeled data, reducing the generalizability of conventional machine learning and limiting the applicability of complex deep learning models. This study proposes SAGE (Spatially Augmented Graph Embeddings), a structurally informed feature-engineering framework that combines controlled noise-based data augmentation with neighborhood-based graph embeddings to improve...
-
40
FleetSieve: Decision-Critical Profiling for SLO-Aware LLM Fleet Configuration
Huang Cheng, Scott Zhang, Aubert Li
cs.LG · cs.DC
Choosing tensor-parallel (TP) degrees and replica counts for an LLM serving fleet is difficult because performance is not monotonic in TP and the feasible choice can change with load. Exhaustive profiling resolves this uncertainty, but measures many configurations that do not affect the final resource allocation. We present FleetSieve, which selects measurements according to their expected effect on a resource-coupled, SLO-aware fleet...
-
41
Rationally Enriched Chebyshev Trunk Bases for DeepONet Surrogates of High Péclet Entrance Transport
Mingeun Choi, Satish Kumar
cs.LG · math.NA
This study demonstrates a rationally enriched Chebyshev (REC) trunk for deep operator network (DeepONet) surrogate models of singularly perturbed and high-Péclet transport problems whose solution profiles are characterized by thin localized boundary or wall layers. The REC trunk combines Chebyshev polynomial dictionary elements with rational dictionary elements constructed using the adaptive Antoulas-Anderson (AAA) algorithm. Over five...
-
42
DeltaML-Bench: Evaluating Machine Learning Agents on Real-World Research Repositories
Josias Moukpe, Priyanka Aryal, Matthew Kenney
cs.LG · cs.AI
Autonomous agents for machine learning experimentation must navigate heterogeneous repositories, repair training pipelines, and evaluate candidate improvements under realistic compute constraints. Existing benchmarks only partially capture these conditions. We introduce DeltaML-Bench, a benchmark comprising 48 tasks sourced from research papers that require agents to improve published baselines within imperfect, open-source repositories. We...
-
43
Time-Uniform Self-Normalized Concentration for Discounted Least Squares: Limits and Corrections
Yi-Shan Wu
cs.LG · stat.ML
Self-normalized concentration inequalities are standard tools in bandit and reinforcement-learning analyses. A widely used weighted extension claims an analogous time-uniform guarantee for discounted least-squares estimators in non-stationary problems. A simple scalar Gaussian counterexample with a fixed parameter shows that the claimed bounded radius is crossed with probability one. For fixed discount and regularization parameters, we...
-
44
Complementary, Not Cumulative: Interaction Effects in Physics-Informed Neural Networks for Navier-Stokes Vortex Shedding
Devesh Shah
cs.LG · physics.flu-dyn
Physics-informed neural networks (PINNs) embed governing partial differential equations directly into the training loss, offering a promising alternative to costly CFD solvers for unsteady flows. Yet the growing list of techniques proposed to improve PINN training is typically validated one at a time, leaving open whether these techniques actually compose. We study this question in depth on the DFG/Schafer-Turek unsteady cylinder wake...
-
45
Unregularized Convergence of Single-Loop, Entropy-Regularized Natural Actor-Critic
Zhiqiang Tan
cs.LG
While entropy regularization is widely used to stabilize and accelerate Natural Policy Gradient methods, its ability to yield faster convergence rates for the unregularized objective remains underexplored. Existing analyses often rely on double-loop architectures and invoke a linear entropy penalty. To bridge the gap between theory and practice, we analyze a single-loop, entropy-regularized Natural Actor-Critic algorithm under compatible...
-
46
Kähler landscapes for complex neural network descents and guarantees including a search and destroy of the Calabi-Yau manifold
Andrew Gracyk
cs.LG · math.DG · stat.ML
We study landscapes for complex-parameterized networks. Our approach is motivated with an information-theoretic manifold perspective of the parameter and via classical optimization guarantees although of complex geometric variety such as through Dolbeault asymptotics. The descent path admits a Kähler information metric under a cross-entropy via the Wirtinger Hessian on the log-likelihood potential. We restrict attention to a descent update...
-
47
A Two-Stage Time-Aware Transformer for Short-Horizon AECOPD Risk Prediction
Dongyang Wang, Weihao Qu, Ling Zheng, Haowen Pan
cs.LG
Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) can worsen rapidly, making timely prediction a clinical priority. Most existing machine learning approaches rely on episodically collected clinical variables, introducing delays that limit their practical utility in home monitoring settings. Home ventilators offer a lower-latency alternative, producing a near-continuous record of respiratory status during daily use. However...
-
48
DraftFM: A FoundationModel for Day-Zero Drafting in Magic: The Gathering
Brian Ward
cs.LG · cs.AI
Drafting a new Magic: The Gathering expansion begins before any pick from it has been observed: the complete card list is public, but the draft logs that supervised pick models train on do not yet exist. We study this day-zero regime directly. DraftFM is a discrete-choice policy that scores exactly the cards available in the current pack, conditioned on the drafted pool and the state of the draft. Every card enters as a frozen 775-dimensional...
-
49
Continuous Adversarial MeanFlow Transfer
Yara Bahram, Zahra Dehghani, Mélodie Desbos, Eric Granger, Pablo Piantanida, Mohammadhadi Shateri
cs.LG · cs.CV
Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to a new domain leaves its costly multi-step sampling unaddressed, and existing acceleration methods are tied to the source parameterization--$ε$, $x$, $v$, or $u$--leaving heterogeneous pretrained models with no common acceleration target. Second, while adversarial refinement is proven effective...
-
50
In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models
Benjamin Smith, Levin Kuhlmann, Kaushik Roy, Gideon Kowadlo
cs.LG · cs.AI
Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared to biological learning systems. Machine learning algorithms typically trade off retention of previously learned information and adaptation to new or changing data patterns. When continual learning capabilities are absent, algorithms must undergo retraining using the entire data set,...
-
51
Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models
Sandra Leticia Juárez-Osorio, Jorge I. Hernandez-Martinez, Jesus Ivan Ruiz-Martinez, Andres Mendez-Vazquez, Eduardo...
cs.LG
We characterize the learning dynamics of a compact hybrid quantum forecasting model through comparison with a structurally aligned classical baseline. Using stationary harmonic-mixture and nonstationary chirp benchmarks with controlled spectral complexity and data availability, we analyze empirical Neural Tangent Kernel dynamics through kernel-target alignment, kernel drift, spectral concentration, and training loss. The classical model...
-
52
Beyond Multimodal Alignment: Certifying Physical Language through Response Substitution and Ordered Execution
Kaizhen Tan, Xin Xu, Siru Tao, Yixiao Li, Hanzhe Hong, Yang Feng, Heqing Du
cs.LG · cs.RO
World models increasingly treat compact multimodal representations as interfaces between perception and physical interaction, yet existing probes do not establish whether different sensors carry the same executable meaning or whether that meaning survives a new action composition. We introduce an operational capability hierarchy and the Disjoint-Bridge Operator-Substitution Certificate (DBOSC), which asks whether independently trained...
-
53
DeltaMomentum: A Key-Value based Anisotropic Momentum Update via Delta Rule
Euijin Hong, Guannan Qu
cs.LG · cs.CL · math.OC · stat.ML
Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate. However, the inputs a deep network sees during training can be highly anisotropic, with a few directions queried frequently while most are seen rarely. Recent methods address this anisotropy by wrapping extra processing around this buffer, leaving the momentum update itself unchanged. We propose...
-
54
When to Retrain: An Empirical Study of Retraining Policies for Streaming ML Under Concept Drift, Budget, and Latency Constraints
Sawan Dasari
cs.LG
Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain. Retraining is costly, retraining budgets are finite, and a retrained model does not take effect instantly: training and deployment latency leave a stale model serving predictions while the data continues to move. We present a controlled empirical study of three practical model-refresh policies (periodic...
-
55
LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection
Tu Anh Hoang Nguyen, Dang Nguyen, Thuc Duy Le, Trung Le, Sunil Gupta
cs.LG
Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations. Existing detectors rely on geometric or reconstruction signals, while prior LLM-based approaches mainly fine-tune LLMs with normal samples or generate synthetic anomalies. We propose LLM-Detector, a framework that utilizes the in-context learning capacity of LLMs for...
-
56
Quantifying Event Impacts on Time Series via Multiscale Contrastive Learning
Yiming Sun, Shengyu Chen, Zhengzhang Chen, Haoyu Wang, Xiaowei Jia, Haifeng Chen
cs.LG
Shocks that spread through the web, such as cybersecurity breach disclosures, can abruptly disrupt financial time series and cause substantial abnormal losses. While these events are disclosed as discrete records through news reports, regulatory filings, or public databases, their consequences unfold through continuous market dynamics. This creates an event-conditioned impact prediction problem: given pre-event market history and limited...
-
57
Longitudinal Bayesian Learning of Continuous Disease Position across the Alzheimer's Disease Continuum
Yingying Zhang, Kun Zhao, Guodong Liu, Qi Huang, Pengfei Gu, Dongchul Kim, Erik Enriquez, Alex D. Leow, Paul M....
cs.LG · cs.AI · q-bio.QM
Alzheimer's disease (AD) progresses as a continuous biological process, whereas most existing neuroimaging-based artificial intelligence methods remain limited to discrete diagnosis or clinical score prediction from cross-sectional imaging. In this work, we propose Disease Continuum Positioning (DCP), a longitudinal Bayesian Learning framework that continuously estimates disease severity from longitudinal diffusion tensor imaging (DTI)....
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.