On the stability of the stochastic gradient Langevin algorithm with dependent data stream

05/04/2021
by   Miklos Rasonyi, et al.
0

We prove, under mild conditions, that the stochastic gradient Langevin dynamics converges to a limiting law as time tends to infinity, even in the case where the driving data sequence is dependent.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/06/2018

On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case

Stochastic Gradient Langevin Dynamics (SGLD) is a combination of a Robbi...
research
04/10/2023

On the strong stability of ergodic iterations

We revisit processes generated by iterated random functions driven by a ...
research
05/30/2019

On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case

We consider the problem of sampling from a target distribution which is ...
research
12/13/2017

Exponential convergence of testing error for stochastic gradient methods

We consider binary classification problems with positive definite kernel...
research
07/09/2022

Stochastic approximation with decision-dependent distributions: asymptotic normality and optimality

We analyze a stochastic approximation algorithm for decision-dependent p...
research
10/22/2018

Stochastic Gradient MCMC for State Space Models

State space models (SSMs) are a flexible approach to modeling complex ti...
research
10/19/2020

A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions

We propose an adaptively weighted stochastic gradient Langevin dynamics ...

Please sign up or login with your details

Forgot password? Click here to reset