This paper shows that the learning rate schedule used in weight-normalized training is more important than the normalization itself, and proposes a new schedule called AIR that targets the effective learning rate trajectory. Practitioners might care about this because it could help them improve the performance of their models by optimizing their learning rate schedules.
Firehose
Filtered to Papers, tagged “learning rate scheduling” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives