P
Peter Richtárik
Researcher at King Abdullah University of Science and Technology
Publications - 290
Citations - 17288
Peter Richtárik is an academic researcher from King Abdullah University of Science and Technology. The author has contributed to research in topics: Convex function & Coordinate descent. The author has an hindex of 56, co-authored 273 publications receiving 12861 citations. Previous affiliations of Peter Richtárik include The Turing Institute & Moscow Institute of Physics and Technology.
Papers
More filters
Posted Content
Federated Learning: Strategies for Improving Communication Efficiency
Jakub Konečný,H. Brendan McMahan,Felix X. Yu,Peter Richtárik,Ananda Theertha Suresh,Dave Bacon +5 more
TL;DR: Two ways to reduce the uplink communication costs are proposed: structured updates, where the user directly learns an update from a restricted space parametrized using a smaller number of variables, e.g. either low-rank or a random mask; and sketched updates, which learn a full model update and then compress it using a combination of quantization, random rotations, and subsampling.
Posted Content
Federated Optimization: Distributed Machine Learning for On-Device Intelligence
TL;DR: A new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are unevenly distributed over an extremely large number of nodes, is introduced, to train a high-quality centralized model.
Journal ArticleDOI
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
Peter Richtárik,Martin Takáč +1 more
TL;DR: In this paper, a randomized block-coordinate descent method for minimizing the sum of a smooth and a simple nonsmooth block-separable convex function was developed, and it was shown that the algorithm converges linearly.
Journal Article
Generalized Power Method for Sparse Principal Component Analysis
TL;DR: In this paper, a new approach to sparse principal component analysis (sparse PCA) is proposed, which is based on the maximization of a convex function on a compact set.
Posted Content
Generalized power method for sparse principal component analysis
TL;DR: A new approach to sparse principal component analysis (sparse PCA) aimed at extracting a single sparse dominant principal component of a data matrix, or more components at once, respectively is developed.