Perturbed gradient descent with occupation time.
Year: 2020
Type: preprint
Abstract: This paper develops further the idea of perturbed gradient descent, by adapting perturbation with the history of state via the notation of occupation time for saddle points. The proposed algorithm PGDOT is shown to converge at least as fast as perturbed gradient descent (PGD) algorithm, and is guaranteed to avoid getting stuck at saddle points. The analysis is corroborated by experimental results.
Source: arXiv (Cornell University)
Authors: Xin Guo, Jiequn Han, Wenpin Tang
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3020927592
