conftrace_

hessian eigenvector

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

graded non-convexity (1) ill-conditioning (1) top eigenvalues (1) local optimum (1) loss surface (1) spectral preconditioning (1) convergence rate (1) optimization algorithm (1) stochastic gradient descent (1)

Papers

Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions ICML 2024 Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian NeurIPS 2020