Stochastic natural gradient descent draws posterior samples in function
space

v1v2v3v4 (latest)

Stochastic natural gradient descent draws posterior samples in function space

25 June 2018

Samuel L. Smith

Daniel Duckworth

Semon Rezchikov

Jascha Narain Sohl-Dickstein

ArXiv (abs)PDF HTML

Papers citing "Stochastic natural gradient descent draws posterior samples in function space"

5 / 5 papers shown

Title
Stochastic weight matrix dynamics during learning and Dyson Brownian motion Gert Aarts B. Lucini Chanju Park 72 1 0 23 Jul 2024
Upper Bound of Bayesian Generalization Error in Partial Concept Bottleneck Model (CBM): Partial CBM outperforms naive CBM Naoki Hayashi Yoshihide Sawada 65 1 0 14 Mar 2024
Deep Learning is Singular, and That's Good Daniel Murfet Susan Wei Biwei Huang Hui Li Jesse Gell-Redman T. Quella UQCV 79 29 0 22 Oct 2020
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev Tianlin Li Qi Lei Ioannis Panageas 55 20 0 11 Oct 2020
The large learning rate phase of deep learning: the catapult mechanism Aitor Lewkowycz Yasaman Bahri Ethan Dyer Jascha Narain Sohl-Dickstein Guy Gur-Ari ODL 212 241 0 04 Mar 2020