`

Timezone: »

 
Poster
Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
Adil Salim · Dmitry Kovalev · Peter Richtarik

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #161
in Probabilistic Methods -- MCMC »

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.

Keywords: MCMC · Convex Optimization · Optimization · Probabilistic Methods
[ Paper]  [ Poster] 

Author Information

Adil Salim (KAUST)
Dmitry Kovalev (KAUST)
Peter Richtarik (KAUST)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors