arXiv Machine Learning June 25, 2026 By Wei-Cheng Lee, Francesco Orabona

A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak--Ruppert Averaging

Read the original on arXiv Machine Learning →

arXiv:2606. 24981v1 Announce Type: new Abstract: We study linear TD(0) under Markovian sampling, where data are generated along a single trajectory.

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 Machine Learning

Jun 26

High-Probability PL-SGD with Markovian Noise: Optimal Mixing and Tail Dependence

arXiv:2606. 26316v1 Announce Type: new Abstract: We study first-order methods for smooth objectives satisfying the Polyak-\L{}ojasiewicz (PL) condition when gradient samples are generated by an exogenous Markov chain.

By Dhruv Sarkar, Aprameyo Chakrabartty, Vaneet Aggarwal

safety

arXiv Statistics ML

3d ago

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

Hugging Face Trending Papers

4d ago

Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data

We study the last iterate of standard tabular temporal-difference (TD) learning from a single trajectory of a finite Markov reward process. For discount factor $γ$, write $H=(1-γ)^{-1}$, and let $μ_{\...

arXiv Machine Learning

Jun 5

Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

arXiv:2606. 05967v1 Announce Type: cross Abstract: In this paper, we study the finite-time behavior of the TD(0) temporal-difference method with linear function approximation (LFA).

By Ziad Kobeissi (L2S), \'Elo\"ise Berthier (U2IS)

Hugging Face Trending Papers

Jun 4

Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

In this paper, we study the finite-time behavior of the TD(0) temporal-difference method with linear function approximation (LFA). We consider on-policy independent and identically distributed (i.

arXiv Machine Learning

4d ago

High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and $(L_0,L_1)$-Smoothness

arXiv:2505.20817v3 Announce Type: replace-cross Abstract: Gradient clipping is widely used in language-model training to control heavy-tailed gradient noise and can improve convergence guarantees ove...

By Taha El Bakkali El Kadi, Savelii Chezhegov, Aleksandr Beznosikov, Samuel Horv\'ath, Eduard Gorbunov

safety

One email a morning, machine-written

Related stories

High-Probability PL-SGD with Markovian Noise: Optimal Mixing and Tail Dependence

Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data

Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data

Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and $(L_0,L_1)$-Smoothness