activity
20152018
most citedStochastic Dual Coordinate Ascent with Adaptive Probabilities

31 citations · 63 across the 3 of their papers we have counts for

collaborators

5 papers

math.OC2018

Data Sampling Strategies in Stochastic Algorithms for Empirical Risk Minimization

Dominik Csiba

Gradient descent methods and especially their stochastic variants have become highly popular in the last decade due to their efficiency on big data optimization problems. In this t…

math.OC201715 cited

Global Convergence of Arbitrary-Block Gradient Methods for Generalized Polyak-Łojasiewicz Functions

Dominik Csiba, Peter Richtárik

In this paper we introduce two novel generalizations of the theory for gradient descent type methods in the proximal setting. First, we introduce the proportion function, which we…

math.OC2016

Coordinate Descent Face-Off: Primal or Dual?

Dominik Csiba, Peter Richtárik

Randomized coordinate descent (RCD) methods are state-of-the-art algorithms for training linear predictors via minimizing regularized empirical risk. When the number of examples ($…

math.OC201517 cited

Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses

Dominik Csiba, Peter Richtárik

In this work we develop a new algorithm for regularized empirical risk minimization. Our method extends recent techniques of Shalev-Shwartz [02/2015], which enable a dual-free anal…

math.OC201531 cited

Stochastic Dual Coordinate Ascent with Adaptive Probabilities

Dominik Csiba, Zheng Qu, Peter Richtárik

This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification co…