Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses
From MaRDI portal
Publication:5004367
DOI10.1162/neco_a_01388OpenAlexW3159746799MaRDI QIDQ5004367
James Simon, Kristofer E. Bouchard, Andrew Ligeralde, Michael R DeWeese, Neha S. Wadia, Charles G. Frye
Publication date: 30 July 2021
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2003.10397
Related Items
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On the convergence of Newton iterations to non-stationary points
- Implementable tensor methods in unconstrained convex optimization
- Residual and Backward Error Bounds in Minimum Residual Krylov Subspace Methods
- Analysis of Newton’s Method at Irregular Singularities
- MINRES-QLP: A Krylov Subspace Method for Indefinite or Singular Symmetric Systems
- The Fundamental Theorem of Linear Algebra
- Newton-Type Methods for Optimization and Variational Problems