Search Results for author: Mahan Tajrobehkar

Found 1 papers, 0 papers with code

Escaping Saddle Points Efficiently with Occupation-Time-Adapted Perturbations

no code implementations9 May 2020 Xin Guo, Jiequn Han, Mahan Tajrobehkar, Wenpin Tang

Motivated by the super-diffusivity of self-repelling random walk, which has roots in statistical physics, this paper develops a new perturbation mechanism for optimization algorithms.

Cannot find the paper you are looking for? You can Submit a new open access paper.