arXiv Machine Learning June 26, 2026 By Dhruv Sarkar, Aprameyo Chakrabartty, Vaneet Aggarwal

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

Read the original on arXiv Machine Learning →

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.

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.

safety

arXiv Machine Learning

Jun 25

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

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

By Wei-Cheng Lee, Francesco Orabona

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

arXiv Machine Learning

Sep 11

Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret without a Variance Bound

The paper studies contextual bilateral trade with full feedback, showing that action-independent observations eliminate the usual polynomial adaptation penalty seen in heavy-tailed bandits. It presents fully parameter-free algorithms that achieve oracle minimax regret rates without knowing the moment order or scale, and derives new regret bounds for both parametric and nonparametric settings. The key technical insight is a paired squared‑loss statistic whose noise cancels, enabling model selection and yielding regret rates that interpolate between classical nonparametric and linear extremes.

By Hangyi Zhao

arXiv Machine Learning

Jun 3

Bregman meets L\'evy: Stochastic mirror descent with heavy-tailed noise in continuous and discrete time

arXiv:2606. 03769v1 Announce Type: cross Abstract: We study the robustness of stochastic mirror descent (SMD) under heavy-tailed noise, focusing on whether the method retains its convergence guarantees when run with infinite-variance stochastic gradient input.

By Pierre-Louis Cauvin, Panayotis Mertikopoulos

arXiv Machine Learning

Jun 4

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization

arXiv:2602. 05657v2 Announce Type: replace Abstract: The study of tail behaviour of SGD-induced processes has been attracting a lot of interest, due to offering strong guarantees with respect to individual runs of an algorithm.

By Aleksandar Armacki, Dragana Bajovi\'c, Du\v{s}an Jakoveti\'c, Soummya Kar, Ali H. Sayed

arXiv Machine Learning

Jun 25

Minimax PAC Bounds for Learning in Exogenous Contextual MDPs

arXiv:2606. 25170v1 Announce Type: cross Abstract: We study PAC learning in tabular discounted Markov decision processes with exogenous i.

By Corentin Pla, Hugo Richard, Marc Abeille, Vianney Perchet

agents reinforcement-learning

One email a morning, machine-written

Related stories

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

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

Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret without a Variance Bound

Bregman meets L\'evy: Stochastic mirror descent with heavy-tailed noise in continuous and discrete time

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization

Minimax PAC Bounds for Learning in Exogenous Contextual MDPs