Conference proceeding
Stochastic L-BFGS Revisited: Improved Convergence Rates and Practical Acceleration Strategies
CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE (UAI2017)
01/01/2017
Abstract
We revisit the stochastic limited-memory BFGS (L-BFGS) algorithm. By proposing a new framework for analyzing convergence, we theoretically improve the (linear) convergence rates and computational complexities of the stochastic L-BFGS algorithms in previous works. In addition, we propose several practical acceleration strategies to speed up the empirical performance of such algorithms. We also provide theoretical analyses for most of the strategies. Experiments on large-scale logistic and ridge regression problems demonstrate that our proposed strategies yield significant improvements via-a-vis competing state-of-the-art algorithms.
Details
- Title: Subtitle
- Stochastic L-BFGS Revisited: Improved Convergence Rates and Practical Acceleration Strategies
- Creators
- Renbo Zhao - Natl Univ Singapore, Dept ECE ISEM & Math, Singapore, SingaporeWilliam B. Haskell - Natl Univ Singapore, Dept ISEM, Singapore, SingaporeVincent Y. F. Tan - Natl Univ Singapore, Dept ECE & Math, Singapore, Singapore
- Resource Type
- Conference proceeding
- Publication Details
- CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE (UAI2017)
- Publisher
- Auai Press
- Number of pages
- 10
- Language
- English
- Date published
- 01/01/2017
- Academic Unit
- Business Analytics
- Record Identifier
- 9984446402802771
Metrics
10 Record Views