activity
20082023
most citedGeneralized power method for sparse principal component analysis

500 citations · 1.3k across the 52 of their papers we have counts for

collaborators
Showing 2018Show all

15 papers · 1 filter

math.OC2018

New Convergence Aspects of Stochastic Gradient Algorithms

Lam M. Nguyen, Phuong Ha Nguyen, Peter Richtárik +3

The classical convergence analysis of SGD is carried out under the assumption that the norm of the stochastic gradient is uniformly bounded. While this might hold for some loss fun…

math.OC2018

A Stochastic Penalty Model for Convex and Nonconvex Optimization with Big Constraints

Konstantin Mishchenko, Peter Richtárik

The last decade witnessed a rise in the importance of supervised learning applications involving {\em big data} and {\em big models}. Big data refers to situations where the amount…

math.OC2018

SEGA: Variance Reduction via Gradient Sketching

Filip Hanzely, Konstantin Mishchenko, Peter Richtarik

We propose a randomized first order optimization method--SEGA (SkEtched GrAdient method)-- which progressively throughout its iterations builds a variance-reduced estimate of the g…

math.OC2018

Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches

Filip Hanzely, Peter Richtárik

Accelerated coordinate descent is a widely popular optimization algorithm due to its efficiency on large-dimensional problems. It achieves state-of-the-art complexity on an importa…

math.OC2018

Nonconvex Variance Reduced Optimization with Arbitrary Sampling

Samuel Horváth, Peter Richtárik

We provide the first importance sampling variants of variance reduced algorithms for empirical risk minimization with non-convex loss functions. In particular, we analyze non-conve…

math.OC2018

Improving SAGA via a Probabilistic Interpolation with Gradient Descent

Adel Bibi, Alibek Sailanbayev, Bernard Ghanem +2

We develop and analyze a new algorithm for empirical risk minimization, which is the key paradigm for training supervised machine learning models. Our method---SAGD---is based on a…