Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization

01/22/2019
by   Thanh Huy Nguyen, et al.
0

Recent studies on diffusion-based sampling methods have shown that Langevin Monte Carlo (LMC) algorithms can be beneficial for non-convex optimization, and rigorous theoretical guarantees have been proven for both asymptotic and finite-time regimes. Algorithmically, LMC-based algorithms resemble the well-known gradient descent (GD) algorithm, where the GD recursion is perturbed by an additive Gaussian noise whose variance has a particular form. Fractional Langevin Monte Carlo (FLMC) is a recently proposed extension of LMC, where the Gaussian noise is replaced by a heavy-tailed α-stable noise. As opposed to its Gaussian counterpart, these heavy-tailed perturbations can incur large jumps and it has been empirically demonstrated that the choice of α-stable noise can provide several advantages in modern machine learning problems, both in optimization and sampling contexts. However, as opposed to LMC, only asymptotic convergence properties of FLMC have been yet established. In this study, we analyze the non-asymptotic behavior of FLMC for non-convex optimization and prove finite-time bounds for its expected suboptimality. Our results show that the weak-error of FLMC increases faster than LMC, which suggests using smaller step-sizes in FLMC. We finally extend our results to the case where the exact gradients are replaced by stochastic gradients and show that similar results hold in this setting as well.

READ FULL TEXT
research
03/25/2019

Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Learning in the Big Data Regime

Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) is a momentum versio...
research
05/27/2022

Constrained Langevin Algorithms with L-mixing External Random Variables

Langevin algorithms are gradient descent methods augmented with additive...
research
02/13/2020

Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise

Stochastic gradient descent with momentum (SGDm) is one of the most popu...
research
06/12/2017

Fractional Langevin Monte Carlo: Exploring Lévy Driven Stochastic Differential Equations for Markov Chain Monte Carlo

Along with the recent advances in scalable Markov Chain Monte Carlo meth...
research
09/19/2022

On the Theoretical Properties of Noise Correlation in Stochastic Optimization

Studying the properties of stochastic noise to optimize complex non-conv...
research
01/19/2021

On Monte-Carlo methods in convex stochastic optimization

We develop a novel procedure for estimating the optimizer of general con...

Please sign up or login with your details

Forgot password? Click here to reset