惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Cyberwarzone
Cyberwarzone
T
Tenable Blog
A
Arctic Wolf
P
Palo Alto Networks Blog
P
Privacy International News Feed
S
Securelist
Security Latest
Security Latest
AWS News Blog
AWS News Blog
W
WeLiveSecurity
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Apple Machine Learning Research
Apple Machine Learning Research
K
Kaspersky official blog
C
CERT Recently Published Vulnerability Notes
V
V2EX - 技术
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Scott Helme
Scott Helme
C
Check Point Blog
TaoSecurity Blog
TaoSecurity Blog
Microsoft Azure Blog
Microsoft Azure Blog
D
DataBreaches.Net
T
Tailwind CSS Blog
T
Tor Project blog
宝玉的分享
宝玉的分享
博
博客园 - 司徒正美
Engineering at Meta
Engineering at Meta
Cisco Talos Blog
Cisco Talos Blog
Recent Announcements
Recent Announcements
H
Hackread – Cybersecurity News, Data Breaches, AI and More
L
Lohrmann on Cybersecurity
Jina AI
Jina AI
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
P
Proofpoint News Feed
IT之家
IT之家
S
Schneier on Security
MyScale Blog
MyScale Blog
S
Security Affairs
Simon Willison's Weblog
Simon Willison's Weblog
C
Comments on: Blog
aimingoo的专栏
aimingoo的专栏
腾
腾讯CDC
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
博
博客园_首页
F
Fortinet All Blogs
Vercel News
Vercel News
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
E
Exploit-DB.com RSS Feed
A
About on SuperTechFans
Help Net Security
Help Net Security
博
博客园 - 【当耐特】
L
LINUX DO - 最新话题

cs.LG updates on arXiv.org

PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction A High-Resolution Landscape Dataset for Concept-Based XAI With Application to Species Distribution Models Rethinking Uncertainty in Segmentation: From Estimation to Decision DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery Deep Spatially-Regularized and Superpixel-Based Diffusion Learning for Unsupervised Hyperspectral Image Clustering The Spectrascapes Dataset: Street-view imagery beyond the visible captured using a mobile platform Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation Artificial intelligence application in lymphoma diagnosis with Vision Transformer using weakly supervised training Context Sensitivity Improves Human-Machine Visual Alignment Depth-Resolved Coral Reef Thermal Fields from Satellite SST and Sparse In-Situ Loggers Using Physics-Informed Neural Networks MyoVision: A Mobile Research Tool and NEATBoost-Attention Ensemble Framework for Real Time Chicken Breast Myopathy Detection Automatic Charge State Tuning of 300 mm FDSOI Quantum Dots Using Neural Network Segmentation of Charge Stability Diagram ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection Visual Sparse Steering (VS2): Unsupervised Adaptation for Image Classification using Sparsity-Guided Steering Vectors Frozen Forecasting: A Unified Evaluation Hybrid Approach for Enhancing Lesion Segmentation in Fundus Images An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning AudioX: A Unified Framework for Anything-to-Audio Generation The Gaussian Latent Machine: Efficient Prior and Posterior Sampling for Inverse Problems Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling A Function-Centric Perspective on Flat and Sharp Minima A Faster Path to Continual Learning Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarks Selectivity and Shape in the Design of Forward-Forward Goodness Functions The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation Spectral Entropy Collapse as a Phase Transition in Delayed Generalisation: An Interventional and Predictive Framework for Grokkin Synthetic Tabular Generators Fail to Preserve Behavioral Fraud Patterns: A Benchmark on Temporal, Velocity, and Multi-Account Signals Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates Automated co-design of high-performance thermodynamic cycles via graph-based hierarchical reinforcement learning Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebysheff Scalarization KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs Does Dimensionality Reduction via Random Projections Preserve Landscape Features? Analog Optical Inference on Million-Record Mortgage Data Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inference Bias-Corrected Adaptive Conformal Inference for Multi-Horizon Time Series Forecasting Counterfactual Peptide Editing for Causal TCR--pMHC Binding Inference Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation Enhancing Confidence Estimation in Telco LLMs via Twin-Pass CoT-Ensembling MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models Physics-informed reservoir characterization from bulk and extreme pressure events with a differentiable simulator Some Theoretical Limitations of t-SNE Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding Beyond Uniform Sampling: Synergistic Active Learning and Input Denoising for Robust Neural Operators Multi-Task LLM with LoRA Fine-Tuning for Automated Cancer Staging and Biomarker Extraction Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration BioTrain: Sub-MB, Sub-50mW On-Device Fine-Tuning for Edge-AI on Biosignals Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction Outperforming Self-Attention Mechanisms in Solar Irradiance Forecasting via Physics-Guided Neural Networks Asymmetric-Loss-Guided Hybrid CNN-BiLSTM-Attention Model for Industrial RUL Prediction with Interpretable Failure Heatmaps From Order to Distribution: A Spectral Characterization of Forgetting in Continual Learning Adaptive Unknown Fault Detection and Few-Shot Continual Learning for Condition Monitoring in Ultrasonic Metal Welding Universality of Gaussian-Mixture Reverse Kernels in Conditional Diffusion Computational framework for multistep metabolic pathway design Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus Monthly Diffusion v0.9: A Latent Diffusion Model for the First AI-MIP Chain of Uncertain Rewards with Large Language Models for Reinforcement Learning SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO From Alignment to Prediction: A Study of Self-Supervised Learning and Predictive Representation Learning LEGO-MOF: Equivariant Latent Manipulation for Editable, Generative, and Optimizable MOF Design C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions Learning Inference Concurrency in DynamicGate MLP Structural and Mathematical Justification Parameter-efficient Quantum Multi-task Learning Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges Design Space Exploration of Hybrid Quantum Neural Networks for Chronic Kidney Disease Golden Handcuffs make safer AI agents Self-Organizing Maps with Optimized Latent Positions (How) Learning Rates Regulate Catastrophic Overtraining Ordinary Least Squares is a Special Case of Transformer A Bayesian Framework for Uncertainty-Aware Explanations in Power Quality Disturbance Classification Optimization with SpotOptim Physics-Informed Neural Networks for Solving Derivative-Constrained PDEs Jump-Start Reinforcement Learning with Vision-Language-Action Regularization Spectral Thompson sampling Online learning with noisy side observations Soft $Q(\lambda)$: A multi-step off-policy method for entropy regularised reinforcement learning using eligibility traces Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate Composite Silhouette: A Subsampling-based Aggregation Strategy RPS: Information Elicitation with Reinforcement Prompt Selection UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization Beyond State Consistency: Behavior Consistency in Text-Based World Models SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention Simulation-Based Optimisation of Batting Order and Bowling Plans in T20 Cricket Hardware-Efficient Neuro-Symbolic Networks with the Exp-Minus-Log Operator Drowsiness-Aware Adaptive Autonomous Braking System based on Deep Reinforcement Learning for Enhanced Road Safety Evaluating Supervised Machine Learning Models: Principles, Pitfalls, and Metric Selection MolCryst-MLIPs: A Machine-Learned Interatomic Potentials Database for Molecular Crystals DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
Asymptotically Optimal Sequential Testing with Markovian Data
[Submitted on 19 Feb 2026 (v1), last revised 29 May 2026 (this v · 2026-06-01 · via cs.LG updates on arXiv.org

View PDF HTML (experimental)

Abstract:We study one-sided and $\alpha$-correct sequential hypothesis testing for data generated by an ergodic, finite-state Markov chain. The null hypothesis is that the unknown transition matrix belongs to a prescribed set $P$ of stochastic matrices, and the alternative corresponds to a disjoint set $Q$. We establish a non-asymptotic instance-dependent lower bound on the expected stopping time of any valid sequential test under the alternative, which is asymptotically tight. Our novel analysis improves the existing lower bounds, which are either asymptotic or provably sub-optimal in this setting. Our lower bound incorporates both the stationary distribution and the transition structure induced by the unknown Markov chain. We further propose an optimal test whose expected stopping time matches this lower bound asymptotically as $\alpha \to 0$. We illustrate the usefulness of our framework through applications to sequential detection of model misspecification in Markov Chain Monte Carlo and to testing structural properties, such as the linearity of transition dynamics, in Markov decision processes. Our findings yield a sharp and general characterization of optimal sequential testing procedures under Markovian dependence.

Submission history

From: Alhad Sethi [view email]
[v1] Thu, 19 Feb 2026 18:11:02 UTC (1,303 KB)
[v2] Fri, 29 May 2026 10:41:53 UTC (1,318 KB)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。