Domain-Independent Dominance of Adaptive Methods

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021(2021)

Cited 19|Views103
No score
Abstract
From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned. We observe that the power of our method is partially explained by a decoupling of learning rate and adaptability, greatly simplifying hyperparameter search. In light of this observation, we demonstrate that, against conventional wisdom, Adam can also outperform SGD on vision tasks, as long as the coupling between its learning rate and adaptability is taken into account. In practice, AvaGrad matches the best results, as measured by generalization accuracy, delivered by any existing optimizer (SGD or adaptive) across image classification (CIFAR, ImageNet) and character-level language modelling (Penn Treebank) tasks. When training GANs, AvaGrad improves upon existing optimizers.
More
Translated text
Key words
domain-independent dominance,adaptive methods,simplified analysis,AvaGrad,SGD,vision tasks,adaptability,learning rate,greatly simplifying hyperparameter search,existing optimizer,image classification,CIFAR,ImageNet,character-level language modelling tasks,Penn Treebank
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined