Skip to content
conftrace_

layer-wise adaptive rate scaling

2 papers

Explore in graph

Also known as

LARS

Co-occurring keywords · papers mentioning both

gradient descent (2) learning rate scaling (1) layer-wise scaling (1) large batch training (1) adaptive rate scaling (1) multimodal alignment (1) learning rate warmup (1) convergence guarantee (1) learning rate (1) adaptive learning rate (1)

Papers

Data-Efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions WACV 2021 Large Batch Optimization for Deep Learning Using New Complete Layer-Wise Adaptive Rate Scaling AAAI 2021