AI Paper Atlas

Research map / Architectures and efficiency / Quantization

A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization

Xuan Tang, Jichu Li, Difan Zou

ICLR 2026 · Architectures and efficiency › Quantization · approach: Ultra-low-bit LLM quantization

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
reduce mantissa length M (very low) for quantized training (ablation)Adam and Muon · Rosenbrock, CIFAR-10 MLP, nanoGPTconvergence / gradient normHurt
increase mantissa length to moderate values (ablation)Adam and Muon · Rosenbrock, CIFAR-10 MLP, nanoGPTconvergence vs full precisionImproved
increase mantissa bit-length (ablation)Adam and Muon · Rosenbrock (10,000 iterations)converged gradient normImproved
push beta2 toward 1 under quantization (ablation)Adam · synthetic and real-data experimentssensitivity to quantization errorHurt
use Muon instead of AdamW under low-precision trainingnanoGPT on OpenWebText · nanoGPT (26M parameters) low-precision trainingtraining robustnessImproved

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