Papers › Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates

Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates

2 Jun 2022arXiv:2206.00832archive 2025-07-28

Jacob Portes, Davis Blalock, Cory Stephenson, Jonathan Frankle

Benchmarking the tradeoff between neural network accuracy and training time is computationally expensive. Here we show how a multiplicative cyclic learning rate schedule can be used to construct a tradeoff curve in a single training run. We generate cyclic tradeoff curves for combinations of training methods such as Blurpool, Channels Last, Label Smoothing and MixUp, and highlight how these cyclic tradeoff curves can be used to evaluate the effects of algorithmic choices on network training efficiency.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jacobfulano/cyclic-learning-rate-schedules officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Benchmarking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Label Smoothing

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections