arXiv Machine Learning August 5, 2026 By Patrick Forr\'e

A Direct Route to Markov Chain Convergence via Asymptotic Equivalence with the Target

Read the original on arXiv Machine Learning →

arXiv:2608. 03353v1 Announce Type: cross Abstract: For a Markov kernel $T$ with an invariant probability measure $\pi$, we give a self-contained proof of the Markov chain convergence theorem via a criterion called asymptotic equivalence with the target.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Statistics ML

2d ago

Uniform ergodicity and spectral gap of importance-tempered MCMC with heavy-tailed targets

arXiv:2506.19186v2 Announce Type: replace-cross Abstract: We study the importance-tempered random-walk Metropolis (RWM) algorithm on $\mathbb{R}^d$, which targets the tempered density $\pi_\beta(x) \...

By Quan Zhou

safety

arXiv Machine Learning

Oct 12

Near-Minimax-Optimal Rates for Asynchronous TD Learning with Markovian Data

arXiv:2609. 38880v2 Announce Type: replace-cross Abstract: We study the last iterate of standard importance-weighted temporal-difference (TD) learning from a single trajectory of a finite Markov decision process.

By Yang Peng

reinforcement-learning

arXiv Statistics ML

Aug 27

Provable Non-Acceleration of Standard Strang Splittings of Kinetic Langevin Dynamics

arXiv:2608.25279v1 Announce Type: cross Abstract: The OBABO and BAOAB schemes and the other standard Strang splittings of kinetic (underdamped) Langevin dynamics are widely used Markov chain Monte Ca...

By Nawaf Bou-Rabee

diffusion

arXiv Statistics ML

Oct 1

Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data

arXiv:2609.38880v1 Announce Type: new Abstract: We study the last iterate of standard tabular temporal-difference (TD) learning from a single trajectory of a finite Markov reward process. For discoun...

By Yang Peng

arXiv Machine Learning

Oct 7

A Sharp Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning

arXiv:2605.06866v3 Announce Type: replace Abstract: We study finite-iteration behavior of asynchronous categorical distributional temporal-difference methods, covering scalar categorical TD (CTD) in...

By Ege C. Kaya, Abolfazl Hashemi

Hugging Face Trending Papers

Aug 20

Unregularized Convergence of Single-Loop, Entropy-Regularized Natural Actor-Critic

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.

reinforcement-learning

One email a morning, machine-written

Related stories

Uniform ergodicity and spectral gap of importance-tempered MCMC with heavy-tailed targets

Near-Minimax-Optimal Rates for Asynchronous TD Learning with Markovian Data

Provable Non-Acceleration of Standard Strang Splittings of Kinetic Langevin Dynamics

Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data

A Sharp Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning

Unregularized Convergence of Single-Loop, Entropy-Regularized Natural Actor-Critic