P
Pavel Dvurechensky
Researcher at Russian Academy of Sciences
Publications - 131
Citations - 2068
Pavel Dvurechensky is an academic researcher from Russian Academy of Sciences. The author has contributed to research in topics: Convex optimization & Convex function. The author has an hindex of 22, co-authored 111 publications receiving 1583 citations. Previous affiliations of Pavel Dvurechensky include Moscow Institute of Physics and Technology & National Research University – Higher School of Economics.
Papers
More filters
Proceedings Article
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn’s Algorithm
TL;DR: In this article, two algorithms for approximating the general optimal transport (OT) distance between two discrete distributions of size n, up to accuracy δ(n 2 ) were presented.
Journal ArticleDOI
Stochastic Intermediate Gradient Method for Convex Problems with Stochastic Inexact Oracle
TL;DR: The first method is an extension of the Intermediate Gradient Method proposed by Devolder, Glineur and Nesterov for problems with deterministic inexact oracle and can be applied to problems with composite objective function, both deterministic and stochastic inexactness of the oracle, and allows using a non-Euclidean setup.
Posted Content
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm
TL;DR: The first algorithm analyzed has better dependence on $\varepsilon$ in the complexity bound, but also is not specific to entropic regularization and can solve the OT problem with different regularizers.
Posted Content
An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization
TL;DR: A non-accelerated derivative-free algorithm with a complexity bound similar to the stochastic-gradient-based algorithm, that is, the authors' bound does not have any dimension-dependent factor except logarithmic.
Proceedings Article
On the Complexity of Approximating Wasserstein Barycenters
Alexey Kroshnin,Nazarii Tupitsa,Darina Dvinskikh,Pavel Dvurechensky,Alexander Gasnikov,César A. Uribe +5 more
TL;DR: The complexity of approximating the Wasserstein barycenter of m discrete measures, or histograms of size n, is studied by contrasting two alternative approaches that use entropic regularization, and a novel proximal-IBP algorithm is proposed which is seen as a proximal gradient method.