most citedTransformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost

2 citations · 2 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2022

Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning

HyunJae Lee, Gihyeon Lee, Junhwan Kim +3

Despite the evolution of Convolutional Neural Networks (CNNs), their performance is surprisingly dependent on the choice of hyperparameters. However, it remains challenging to effi…