# Mechanic: A Learning Rate Tuner

**Authors:** Ashok Cutkosky, Aaron Defazio, Harsh Mehta  
**arXiv:** [2306.00144](https://arxiv.org/abs/2306.00144)  
**Date:** 2023-05-31  
**Summary page:** https://www.summarizepaper.com/fr/arxiv-id/2306.00144v1/

## Abstract

We introduce a technique for tuning the learning rate scale factor of any base optimization algorithm and schedule automatically, which we call \textsc{mechanic}. Our method provides a practical realization of recent theoretical reductions for accomplishing a similar goal in online convex optimization. We rigorously evaluate \textsc{mechanic} on a range of large scale deep learning tasks with varying batch sizes, schedules, and base optimization algorithms. These experiments demonstrate that depending on the problem, \textsc{mechanic} either comes very close to, matches or even improves upon manual tuning of learning rates.