M
Martin Takáč
Researcher at Lehigh University
Publications - 147
Citations - 6625
Martin Takáč is an academic researcher from Lehigh University. The author has contributed to research in topics: Computer science & Convex function. The author has an hindex of 33, co-authored 125 publications receiving 5574 citations. Previous affiliations of Martin Takáč include Zayed University & University of Edinburgh.
Papers
More filters
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.
Posted Content
Parallel Coordinate Descent Methods for Big Data Optimization
Peter Richtárik,Martin Takáč +1 more
TL;DR: In this article, the authors show that randomized coordinate descent methods can be accelerated by parallelization when applied to the problem of minimizing the sum of a partially separable smooth convex function and a simple separable convex functions.
Journal ArticleDOI
Parallel coordinate descent methods for big data optimization
Peter Richtárik,Martin Takáč +1 more
TL;DR: This work shows that randomized (block) coordinate descent methods can be accelerated by parallelization when applied to the problem of minimizing the sum of a partially separable smooth convex function and a simple separable conveX function.
Proceedings Article
SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
TL;DR: In this paper, the authors proposed a StochAstic Recursive Gradient Algorithm for finite-sum minimization (SARAH), which admits a simple recursive framework for updating stochastic gradient estimates.
Proceedings Article
Reinforcement learning for solving the vehicle routing problem
TL;DR: This work presents an end-to-end framework for solving the Vehicle Routing Problem (VRP) using reinforcement learning, and demonstrates how this approach can handle problems with split delivery and explore the effect of such deliveries on the solution quality.