Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
credit_assignment [2018/01/23 18:55]
admin
credit_assignment [2019/02/04 18:02]
admin
Line 84: Line 84:
  
 This paper explores an unconventional training method that uses alternating direction methods and Bregman iteration to train networks without gradient descent steps. ​ This paper explores an unconventional training method that uses alternating direction methods and Bregman iteration to train networks without gradient descent steps. ​
 +
 +https://​arxiv.org/​pdf/​1802.05642v1.pdf The Mechanics of n-Player Differentiable Games
 +
 +http://​www.jmlr.org/​papers/​volume18/​17-653/​17-653.pdf Maximum Principle Based Algorithms for Deep Learning
 +
 +https://​github.com/​facebookresearch/​nevergrad