Abstract
This paper presents a framework of successive functional gradient optimization for training non convex models such as neural networks, where training is driven by mirror descent in a function space. We provide a theoretical analysis and empirical study of the training method derived from this framework. It is shown that the method leads to better performance than that of standard training techniques.
| Original language | English (US) |
|---|---|
| Journal | Proceedings of Machine Learning Research |
| Volume | 119 |
| State | Published - 2020 |
| Externally published | Yes |
| Event | 37th International Conference on Machine Learning, ICML 2020 - Virtual, Online Duration: Jul 13 2020 → Jul 18 2020 |
ASJC Scopus subject areas
- Software
- Control and Systems Engineering
- Statistics and Probability
- Artificial Intelligence