Signals 4 · free daily AI digest

Generalization behavior of OPTQ and the role of regularization

Paper recorded by Signals 4 on 2026-09-25 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.LG · 机器学习 · first seen 2026-09-28

Abstract

Large neural networks can be compressed by rounding or "quantizing" their weights to numbers that admit representations with fewer bits. One algorithm for quantization, OPTQ, progressively quantizes the weights of a neural network so that the squared quantization error on a specified calibration dataset is as small as possible. We study the performance of OPTQ and a variant algorithm, stochastic O

Read on arXiv →

#9 most recent of 310 cs.LG papers we have recorded · ↑ newer: Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Wei · ↓ older: Online Learning via Learned Latent Bayesian Tracking
Cite this page: Generalization behavior of OPTQ and the role of regularization: the #9 most recent of 310 cs.LG papers we have recorded (as of 2026-09-25). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/generalization-behavior-of-optq-and-the-role-of-regularization.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions