SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
arXiv preprint arXiv:1902.00618 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A unified framework for exponential tilting in diffusion and flow models that includes bias-variance decompositions showing finite gradient variance for some methods, norm bounds on adjoint ODEs, and adapted losses with new Crooks and Jarzynski identities.
An inexact proximal gradient algorithm with complexity bounds for finding approximate stationary points in minimax problems under local varying KL conditions on the inner problem.
citing papers explorer
-
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
-
A unified perspective on fine-tuning and sampling with diffusion and flow models
A unified framework for exponential tilting in diffusion and flow models that includes bias-variance decompositions showing finite gradient variance for some methods, norm bounds on adjoint ODEs, and adapted losses with new Crooks and Jarzynski identities.
-
A first-order method for nonconvex-nonconcave minimax problems under a local Kurdyka-Lojasiewicz condition
An inexact proximal gradient algorithm with complexity bounds for finding approximate stationary points in minimax problems under local varying KL conditions on the inner problem.