Conference proceeding
Learning with Non-Convex Truncated Losses by SGD
Proceedings of Machine Learning Research , Vol.115, pp.701-711
Uncertainty in Artificial Intelligence Conference, 35th
2020
Abstract
Learning with a convex loss function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper, we study a family of objective functions formed by truncating traditional loss functions, which is applicable to both shallow learning and deep learning. Truncating loss functions has potential to be less vulnerable and more robust to large noise in observations that could be adversarial. More importantly, it is a generic technique without assuming the knowledge of noise distribution. To justify non-convex learning with truncated losses, we establish excess risk bounds of empirical risk minimization based on truncated losses for heavy-tailed output, and statistical error of an approximate stationary point found by stochastic gradient descent (SGD) method. Our experiments for shallow and deep learning for regression with outliers, corrupted data and heavy-tailed noise further justify the proposed method.
Details
- Title: Subtitle
- Learning with Non-Convex Truncated Losses by SGD
- Creators
- Yi XuShenghuo ZhuSen YangChi ZhangRong JinTianbao Yang
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of Machine Learning Research , Vol.115, pp.701-711
- Conference
- Uncertainty in Artificial Intelligence Conference, 35th
- Language
- English
- Date published
- 2020
- Academic Unit
- Computer Science
- Record Identifier
- 9984259500702771
Metrics
11 Record Views