arXiv Machine Learning June 11, 2026 By Shira Vansover-Hager, Matan Schliserman, Ofir Schlisselberg, Tomer Koren

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

Read the original on arXiv Machine Learning →

arXiv:2606. 11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training.

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

2d ago

Fast Regularized Policy Mirror Descent with One-Step TD Updates

arXiv:2609.39837v1 Announce Type: new Abstract: Policy mirror descent (PMD) enjoys fast convergence in regularized Markov decision processes (MDPs), but existing guarantees often rely on exact or inc...

By Qipei Chen, Wenye Li, Yule Sun, Ke Wei

reinforcement-learning

arXiv Machine Learning

2d ago

State-space models through the lens of ensemble control

arXiv:2603.13587v2 Announce Type: replace-cross Abstract: State-space models (SSMs) are effective architectures for sequential modeling, but a rigorous theoretical understanding of their training dyn...

By Ye Feng, Jianfeng Lu

arXiv Machine Learning

Jun 9

A Robust $\widetilde{\mathcal{O}}(1/\sqrt{T})$ Rate for Unprojected TD Learning with Linear Function Approximation

arXiv:2506. 01052v3 Announce Type: replace Abstract: We investigate the finite-time convergence properties of Temporal Difference (TD) learning with linear function approximation, a cornerstone of reinforcement learning.

By Wei-Cheng Lee, Francesco Orabona

reinforcement-learning

arXiv AI

Jul 21

Symmetric Behavior Regularized Policy Optimization

arXiv:2508. 04225v4 Announce Type: replace-cross Abstract: Behavior Regularized Policy Optimization (BRPO) leverages asymmetric divergence regularization to mitigate distribution shift in offline reinforcement learning.

By Lingwei Zhu, Haseeb Shah, Zheng Chen, Martha White

reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 2

Mirror Descent Under Generalized Smoothness

arXiv:2502. 00753v4 Announce Type: replace-cross Abstract: Smoothness is crucial for attaining fast rates in first-order optimization.

By Dingzhi Yu, Wei Jiang, Hongyi Tao, Yuanyu Wan, Lijun Zhang

llms benchmarks

arXiv AI

Jun 2

Stability Analysis of Sharpness-Aware Minimization

arXiv:2301. 06308v2 Announce Type: replace-cross Abstract: Sharpness-aware minimization (SAM) is a training method that seeks to find flat minima in deep learning, resulting in state-of-the-art performance across various domains.

By Hoki Kim, Jinseong Park, Yujin Choi, Jaewook Lee

diffusion benchmarks

One email a morning, machine-written

Related stories

Fast Regularized Policy Mirror Descent with One-Step TD Updates

State-space models through the lens of ensemble control

A Robust $\widetilde{\mathcal{O}}(1/\sqrt{T})$ Rate for Unprojected TD Learning with Linear Function Approximation

Symmetric Behavior Regularized Policy Optimization

Mirror Descent Under Generalized Smoothness

Stability Analysis of Sharpness-Aware Minimization