A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps
cs.LG, math.OC
Submitted: 2026-08-16
Updated: 2026-09-25
Terminology
Sources
- Mini-Batch Stochastic Halpern Algorithm for Nonexpansive Fixed Point Problems
- Large Deviations of Vector-valued Martingales in 2-Smooth Normed Spaces
- A Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning
- Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
- Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process
- Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks