paper-with-me

Papers

Muon Converges under Heavy-Tailed Noise: Nonconvex Hölder-Smooth Empirical Risk Minimization

2026-03-16 · Hideaki Iiduka arxiv

Muon is a recently proposed optimizer that enforces orthogonality in parameter updates by projecting gradients onto the Stiefel manifold, leading to stable and efficient training in large-scale deep neural networks. Meanwhile, the previously reported results indicated that stochastic noise in practical machine learning may exhibit heavy-tailed behavior, violating the bounded-variance assumption. In this paper, we consider the problem of minimizing a nonconvex Hölder-smooth empirical risk that works well with the heavy-tailed stochastic noise. We then show that Muon converges to a stationary point of the empirical risk under the boundedness condition accounting for heavy-tailed stochastic noise. In addition, we show that Muon converges faster than mini-batch SGD.

📄 PDF Abstract BibTeX arXiv:2603.15059

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction

2026-03-10 · Tianyu Pang, Yujie Fang, Zihang Liu, Shenyang Deng 외 arxiv

Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon's orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and o…

Image Classification

Federated Stochastic Minimax Optimization under Heavy-Tailed Noises

2025-11-06 · Xinwen Zhang, Hongchang Gao arxiv

Heavy-tailed noise has attracted growing attention in nonconvex stochastic optimization, as numerous empirical studies suggest it offers a more realistic assumption than standard bounded variance assumption. In this work…

Stochastic OptimizationFederated Learning

Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives

2026-05-12 · Konstantinos Oikonomidis, Jan Quan, Kimon Antonakopoulos, Antonio Silveti-Falls 외 arxiv

In this work, we develop proximal preconditioned gradient methods with a focus on spectral gradient methods providing a proximal extension to the Muon and Scion optimizers. We introduce a family of stochastic algorithms …

Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise

2026-02-07 · Dingzhi Yu, Hongyi Tao, Yuanyu Wan, Luo Luo 외 arxiv

While adaptive gradient methods are the workhorse of modern machine learning, sign-based optimization algorithms such as Lion and Muon have recently demonstrated superior empirical performance over AdamW in training larg…

Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?

2026-06-22 · Dingzhi Yu, Hongyi Tao, Yuanyu Wan, Luo Luo 외 arxiv

AdamW is the de facto optimizer for training large language models (LLMs), yet the theory behind it still lives mostly in finite-variance regimes. This is increasingly unsatisfying, as empirical evidence indicates that s…