Name
Abstract | ||
|---|---|---|
We investigate a reduction of supervised learning to game playing that reveals new connections and learning methods. For convex one-layer problems, we demonstrate an equivalence between global minimizers of the training problem and Nash equilibria in a simple game. We then show how the game can be extended to general acyclic neural networks with differentiable convex gates, establishing a bijection between the Nash equilibria and critical (or KKT) points of the deep learning problem. Based on these connections we investigate alternative learning methods, and find that regret matching can achieve competitive training performance while producing sparser models than current deep learning strategies. |
Year | Venue | DocType |
|---|---|---|
2016 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016) | Conference |
Volume | ISSN | Citations |
29 | 1049-5258 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dale Schuurmans | 1 | 2760 | 317.49 |
| Martin Zinkevich | 2 | 1893 | 160.99 |