Search Results for author: Miklos Rásonyi

Found 1 papers, 0 papers with code

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

no code implementations30 May 2019 Ngoc Huy Chau, Éric Moulines, Miklos Rásonyi, Sotirios Sabanis, Ying Zhang

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017).

Stochastic Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.