arXiv Machine Learning August 13, 2026 By Chenhan Jin, Shengze Xu, Binghui Xie, Kaiwen Zhou, Fan Jia, James Cheng, Tieyong Zeng

Adaptive Bregman Proximal Stochastic Gradient with a Stabilized Barzilai--Borwein Step Size

Read the original on arXiv Machine Learning →

arXiv:2608. 12009v1 Announce Type: cross Abstract: Bregman proximal stochastic gradient (BPSG) methods bring variance-reduced composite optimization to objectives whose geometry is poorly captured by Euclidean smoothness.

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

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

Jun 30

Curvature-Weighted Gradient Diversity: A Noise Measure for Geometry-Adaptive SGD Schedules

arXiv:2606. 30455v1 Announce Type: new Abstract: The standard convergence analysis of mini-batch stochastic gradient descent (SGD) models gradient noise using a single variance term that treats all parameter directions equally, ignoring the fact that noise in high-curvature directions has less impact because learning rates are already constrained there.

By Muhammad Hamza (Indian Institute of Technology Kharagpur), Ayush Goel (Indian Institute of Technology Kharagpur)

arXiv Computer Vision

Aug 26

Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization

arXiv:2502.21099v3 Announce Type: replace-cross Abstract: This paper proposes {\sf AEPG-SPIDER}, an Adaptive Extrapolated Proximal Gradient (AEPG) method with variance reduction for minimizing compos...

By Ganzhao Yuan

arXiv Machine Learning

Jul 28

Learning from the Descent Direction: Adaptive Gradient Descent under One-Sided H\"older Regularity

arXiv:2607. 22906v1 Announce Type: new Abstract: We study adaptive gradient descent for continuously differentiable, possibly nonconvex objectives under one-sided H\"older regularity.

By Arzu Ahmadova, Ismail Huseynov

benchmarks

arXiv Machine Learning

Jun 3

From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization

arXiv:2606. 02948v1 Announce Type: new Abstract: Curvature adaptivity is a classical theme in online optimization: for convex Lipschitz losses, adaptive methods interpolate between the optimal $O(\sqrt{T})$ regret for general convex losses and $O(\log T)$ regret under strong convexity.

By Moses Charikar, Chirag Pabbaraju, Ambuj Tewari

arXiv Machine Learning

Jun 2

Riemannian Stochastic Optimization for Sufficient Dimension Reduction

arXiv:2606. 00413v1 Announce Type: cross Abstract: Sufficient dimension reduction (SDR) makes high-dimensional regression tractable by projecting the covariates onto a low-dimensional subspace that preserves the conditional mean of the response.

By Thibault Pautrel, Fran\c{c}ois Portier

One email a morning, machine-written

Related stories

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

Curvature-Weighted Gradient Diversity: A Noise Measure for Geometry-Adaptive SGD Schedules

Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization

Learning from the Descent Direction: Adaptive Gradient Descent under One-Sided H\"older Regularity

From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization

Riemannian Stochastic Optimization for Sufficient Dimension Reduction