NeurIPS 2018poster165 citations

NEON2: Finding Local Minima via First-Order Oracles

Zeyuan Allen-Zhu, Yuanzhi Li

Abstract

We propose a reduction for non-convex optimization that can (1) turn an stationary-point finding algorithm into an local-minimum finding one, and (2) replace the Hessian-vector product computations with only gradient computations. It works both in the stochastic and the deterministic settings, without hurting the algorithm's performance.

BibTeX
@inproceedings{NEURIPS2018_d4b2aeb2,
 author = {Allen-Zhu, Zeyuan and Li, Yuanzhi},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {NEON2: Finding Local Minima via First-Order Oracles},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/d4b2aeb2453bdadaa45cbe9882ffefcf-Paper.pdf},
 volume = {31},
 year = {2018}
}