paper-with-me

Papers

Optimistic Dual Averaging Unifies Modern Optimizers

2026-05-11 · Thomas Pethick, Wanyun Xie, Roman Machacek, Volkan Cevher arxiv

We introduce SODA, a generalization of Optimistic Dual Averaging, which provides a common perspective on state-of-the-art optimizers like Muon, Lion, AdEMAMix and NAdam, showing that they can all be viewed as optimistic instances of this framework. Based on this framing, we propose a practical SODA wrapper for any base optimizer that eliminates weight decay tuning through a theoretically-grounded $1/k$ decay schedule. Empirical results across various scales and training horizons show that SODA consistently improves performance without any additional hyperparameter tuning.

📄 PDF Abstract BibTeX arXiv:2605.11172

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Layer-wise Quantization for Quantized Optimistic Dual Averaging

2025-05-20 · Anh Duc Nguyen, Ilia Markov, Frank Zhengqing Wu, Ali Ramezani-Kebrya 외

Modern deep neural networks exhibit heterogeneity across numerous layers of various types such as residuals, multi-head attention, etc., due to varying structures (dimensions, activation functions, etc.), distinct repres…

Quantization

Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs

2025-12-18 · Aaron Defazio, Konstantin Mishchenko, Parameswaran Raman, Hao-Jun Michael Shi 외 arxiv

We propose Generalized Primal Averaging (GPA), an extension of Nesterov's method that unifies and generalizes recent averaging-based optimizers like single-worker DiLoCo and Schedule-Free, within a non-distributed settin…

Unifying mirror descent and dual averaging

2019-10-30 · Anatoli Juditsky, Joon Kwon, Éric Moulines

We introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this family, we define new algorithms for constra…

Tight Last-Iterate Convergence of the Extragradient and the Optimistic Gradient Descent-Ascent Algorithm for Constrained Monotone Variational Inequalities

2022-04-20 · Yang Cai, Argyris Oikonomou, Weiqiang Zheng

The monotone variational inequality is a central problem in mathematical programming that unifies and generalizes many important settings such as smooth convex optimization, two-player zero-sum games, convex-concave sadd…

Riemannian Lyapunov Optimizer: A Unified Framework for Optimization

2026-01-29 · Yixuan Wang, Omkar Sudhir Patil, Warren E. Dixon arxiv

We introduce Riemannian Lyapunov Optimizers (RLOs), a family of optimization algorithms that unifies classic optimizers within one geometric framework. Unlike heuristic improvements to existing optimizers, RLOs are syste…