Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients
stat.ML, cs.LG, cs.NA, math.NA
Submitted: 2026-01-31
Updated: 2026-11-07
Comments: The 40th Conference on Neural Information Processing Systems (NeurIPS 2026)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Markov Chain Variance Estimation: A Stochastic Approximation Approach
- A Non-Asymptotic Theory of Seminorm Lyapunov Stability: From Deterministic to Stochastic Iterative Algorithms
- Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis
- Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning
- Faster Fixed-Point Methods for Multichain MDPs
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference