PaperHub

暂无评分数据

ICLR 2024

Locally Optimal Descent for Adaptive Stepsize Scheduling

OpenReviewPDF
提交: 2023-09-22更新: 2024-03-26
TL;DR

We introduce a dynamic stepsize scheduler based on the local optimal step size, it attains optimal rate in the smooth (non-convex) setting and empirically shown to perform on par with manually fine-tuned schedulers.

摘要

关键词
step-size tuningoptimizationnon-convexlearning rate schedulers

评审与讨论

暂无评审记录