Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers

arXiv:2605.18106 · math.OC, cs.AI, cs.LG, stat.ML · Submitted 2026-05-18 · Read on arXiv

math.OC, cs.AI, cs.LG, stat.ML

Submitted: 2026-05-18

Updated: 2026-10-14

Terminology

• Adam — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Online Control via Counterfactual Tracking
• Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability
• Petrov-Galerkin operator inference with application to stability-encouraging identification