Conference proceeding
Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, Vol.97
Proceedings of Machine Learning Research
01/01/2019
Abstract
Difference of convex (DC) functions cover a broad family of non-convex and possibly non-smooth and non-differentiable functions, and have wide applications in machine learning and statistics. Although deterministic algorithms for DC functions have been extensively studied, stochastic optimization that is more suitable for learning with big data remains under-explored. In this paper, we propose new stochastic optimization algorithms and study their first-order convergence theories for solving a broad family of DC functions. We improve the existing algorithms and theories of stochastic optimization for DC functions from both practical and theoretical perspectives. Moreover, we extend the proposed stochastic algorithms for DC functions to solve problems with a general non-convex non-differentiable regularizer, which does not necessarily have a DC decomposition but enjoys an efficient proximal mapping. To the best of our knowledge, this is the first work that gives the first non-asymptotic convergence for solving non-convex optimization whose objective has a general non-convex non-differentiable regularizer.
Details
- Title: Subtitle
- Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence
- Creators
- Yi Xu - University of IowaQi Qi - University of IowaQihang Lin - University of IowaRong Jin - Bellevue Hospital CenterTianbao Yang - Univ Iowa, Dept Comp Sci, Iowa City, IA 52242 USA
- Contributors
- K Chaudhuri (Editor)R Salakhutdinov (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, Vol.97
- Publisher
- JMLR-JOURNAL MACHINE LEARNING RESEARCH
- Series
- Proceedings of Machine Learning Research
- ISSN
- 2640-3498
- Number of pages
- 10
- Grant note
- IIS-1545995 / National Science Foundation; National Science Foundation (NSF)
- Language
- English
- Date published
- 01/01/2019
- Academic Unit
- Business Analytics; Computer Science
- Record Identifier
- 9984380417902771
Metrics
12 Record Views