AI Paper Atlas

Research map / Optimization / Optimizers

General Analysis of LMO-based Optimizers: Beyond Bounded Variance

Egor Shulgin, Mohamed Awad, Peter Richtárik, Eduard Gorbunov

ICML 2026 · Optimization › Optimizers · approach: SGD momentum and step-size schedules

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase momentum alpha (ablation)Muon (idealized) on matrix regression · Matrix regression, eps = 10^-1empirical critical batch size: bcrit = 1 -> bcrit = 16 (alpha 0.1 -> 0.9)Improved
increase momentum alpha with larger batch size (optimal momentum grows with batch) (ablation)normalized SGD with momentum · Linear regression, eps = 10^-2optimal batch size: b* = 1 for alpha <= 0.5, larger for higher alphaImproved
use full-batch updates for a harder target accuracy (ablation)normalized SGD with momentum · Linear regression, eps = 5e-3sample complexityImproved
increase batch size under bounded-variance theoryLMO-family methods · theorysample complexityHurt
increase momentum from 0.1 to 0.2 (ablation)Muon/AdamW mix on NanoGPT (~6M params) · WikiText-103, validation loss < 3.9epochs to target lossMixed
increase batch size (ablation)Muon/AdamW mix on NanoGPT · WikiText-103optimal step sizeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy