Name
Abstract | ||
|---|---|---|
We propose a new algorithm-Stochastic Proximal Langevin Algorithm (SPLA)-for sampling from a log concave distribution. Our method is a generalization of the Langevin algorithm to potentials expressed as the sum of one stochastic smooth term and multiple stochastic nonsmooth terms. In each iteration, our splitting technique only requires access to a stochastic gradient of the smooth term and a stochastic proximal operator for each of the nonsmooth terms. We establish nonasymptotic sublinear and linear convergence rates under convexity and strong convexity of the smooth term, respectively, expressed in terms of the KL divergence and Wasserstein distance. We illustrate the efficiency of our sampling technique through numerical simulations on a Bayesian learning task. |
Year | Venue | Keywords |
|---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | wasserstein distance,sampling techniques,sampling technique,kl divergence |
Field | DocType | Volume |
Sublinear function,Convexity,Bayesian inference,Algorithm,Operator (computer programming),Rate of convergence,Sampling (statistics),Mathematics,Kullback–Leibler divergence | Journal | 32 |
ISSN | Citations | PageRank |
1049-5258 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Adil Salim | 1 | 2 | 4.42 |
| Kovalev, Dmitry | 2 | 1 | 4.40 |
| Peter Richtárik | 3 | 1314 | 84.53 |