Negative eigenvalues of the Hessian in deep neural networks
2018
The loss function of deep networks is known to be non-convex but the precise nature of this nonconvexity is still an active area of research. In this work, we study the loss landscape of deep networks through the eigendecompositions of their Hessian matrix. In particular, we examine how important the negative eigenvalues are and the benefits one can observe in handling them appropriately.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
20
References
22
Citations
NaN
KQI