Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization - Département Image, Données, Signal Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

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

Résumé

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 asymp-totic 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 stochas-tic gradients and show that similar results hold in this setting as well.
Fichier principal
Vignette du fichier
nguyen19c.pdf (391.81 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02346147 , version 1 (04-11-2019)

Identifiants

  • HAL Id : hal-02346147 , version 1

Citer

Thanh Huy Nguyen, Umut Şimşekli, Gael Richard. Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization. International Conference on Machine Learning (ICML), Jun 2019, Long Beach, United States. ⟨hal-02346147⟩
47 Consultations
68 Téléchargements

Partager

Gmail Facebook X LinkedIn More