12/07/2020

Low-loss connection of weight vectors: distribution-based approaches

Ivan Anokhin, Dmitry Yarotsky

Keywords: Deep Learning - Theory

Abstract: Recent research shows that sublevel sets of the loss surfaces of overparameterized networks are connected, exactly or approximately. We describe and compare experimentally a panel of methods used to connect two low-loss points by a low-loss curve on this surface. Our methods vary in accuracy and complexity. Most of our methods are based on ''macroscopic'' distributional assumptions and are insensitive to the detailed properties of the points to be connected. Some methods require a prior training of a ''global connection model'' which can then be applied to any pair of points. The accuracy of the method generally correlates with its complexity and sensitivity to the endpoint detail.

 0
 0
 0
 0
This is an embedded video. Talk and the respective paper are published at ICML 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers