Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

Jie Ji; Gen Li; Lu Yin; Minghai Qin; Geng Yuan; Linke Guo; Shiwei Liu; Xiaolong Ma

2024 ICML ICML 2024

Advancing Dynamic Sparse Training by Exploring Optimization Opportunities

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Jie Ji, Gen Li, Lu Yin, Minghai Qin, Geng Yuan, Linke Guo, Shiwei Liu, Xiaolong Ma

Topics

Machine Learning > Optimization & Theory > Optimization Machine Learning > Application Areas > Efficient Computing Deep Learning > Architectures > Neural Networks

Keywords

bilevel optimization dynamic sparse training weights execution speed mask sparse patterns

Download PDF