Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Martin Takáč

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods


Feb 19, 2021
Zheng Shi, Nicolas Loizou, Peter Richtárik, Martin Takáč


  Access Paper or Ask Questions

Reinforcement Learning based Multi-Robot Classification via Scalable Communication Structure


Dec 18, 2020
Guangyi Liu, Arash Amini, Martin Takáč, Héctor Muñoz-Avila, Nader Motee


  Access Paper or Ask Questions

DynNet: Physics-based neural architecture design for linear and nonlinear structural response modeling and prediction


Jul 03, 2020
Soheil Sadeghi Eshkevari, Martin Takáč, Shamim N. Pakzad, Majid Jahani

* Submitted to Elsevier 

  Access Paper or Ask Questions

Constrained Combinatorial Optimization with Reinforcement Learning


Jun 22, 2020
Ruben Solozabal, Josu Ceberio, Martin Takáč


  Access Paper or Ask Questions

SONIA: A Symmetric Blockwise Truncated Optimization Algorithm


Jun 06, 2020
Majid Jahani, Mohammadreza Nazari, Rachael Tappenden, Albert S. Berahas, Martin Takáč

* 38 pages, 74 figures 

  Access Paper or Ask Questions

Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations


Jun 02, 2020
Zheng Shi, Nur Sila Gulgec, Albert S. Berahas, Shamim N. Pakzad, Martin Takáč

* 38 pages, 48 figures 

  Access Paper or Ask Questions

Distributed Fixed Point Methods with Compressed Iterates


Dec 20, 2019
Sélim Chraibi, Ahmed Khaled, Dmitry Kovalev, Peter Richtárik, Adil Salim, Martin Takáč

* 15 pages, 4 algorithms, 4 Theorems 

  Access Paper or Ask Questions

FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods


Oct 29, 2019
Nur Sila Gulgec, Zheng Shi, Neil Deshmukh, Shamim Pakzad, Martin Takáč

* Paper accepted to NeurIPS workshop 

  Access Paper or Ask Questions

A Layered Architecture for Active Perception: Image Classification using Deep Reinforcement Learning


Sep 20, 2019
Hossein K. Mousavi, Guangyi Liu, Weihang Yuan, Martin Takáč, Héctor Muñoz-Avila, Nader Motee

* Submitted to ICRA-2020 

  Access Paper or Ask Questions

Scaling Up Quasi-Newton Algorithms: Communication Efficient Distributed SR1


May 30, 2019
Majid Jahani, Mohammadreza Nazari, Sergey Rusakov, Albert S. Berahas, Martin Takáč

* 18 pages, 14 figures 

  Access Paper or Ask Questions

Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework


May 30, 2019
Mohammadreza Nazari, Majid Jahani, Lawrence V. Snyder, Martin Takáč


  Access Paper or Ask Questions

Multi-Agent Image Classification via Reinforcement Learning


May 13, 2019
Hossein K. Mousavi, Mohammadreza Nazari, Martin Takáč, Nader Motee

* Submitted to IROS'19 

  Access Paper or Ask Questions

Quasi-Newton Methods for Deep Learning: Forget the Past, Just Sample


Jan 28, 2019
Albert S. Berahas, Majid Jahani, Martin Takáč

* 45 pages, 26 figures 

  Access Paper or Ask Questions

Distributed Learning with Compressed Gradient Differences


Jan 26, 2019
Konstantin Mishchenko, Eduard Gorbunov, Martin Takáč, Peter Richtárik

* 42 pages 

  Access Paper or Ask Questions

Inexact SARAH Algorithm for Stochastic Optimization


Nov 25, 2018
Lam M. Nguyen, Katya Scheinberg, Martin Takáč


  Access Paper or Ask Questions

New Convergence Aspects of Stochastic Gradient Algorithms


Nov 10, 2018
Lam M. Nguyen, Phuong Ha Nguyen, Peter Richtárik, Katya Scheinberg, Martin Takáč, Marten van Dijk

* Substantial extension of arXiv:1802.03801 

  Access Paper or Ask Questions

Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy


Oct 26, 2018
Majid Jahani, Xi He, Chenxin Ma, Aryan Mokhtari, Dheevatsa Mudigere, Alejandro Ribeiro, Martin Takáč


  Access Paper or Ask Questions

SGD and Hogwild! Convergence Without the Bounded Gradients Assumption


Jun 08, 2018
Lam M. Nguyen, Phuong Ha Nguyen, Marten van Dijk, Peter Richtárik, Katya Scheinberg, Martin Takáč

* Proceedings of the 35th International Conference on Machine Learning, PMLR 80:3747-3755, 2018 

  Access Paper or Ask Questions

Dual Free Adaptive Mini-batch SDCA for Empirical Risk Minimization


May 24, 2018
Xi He, Martin Takáč


  Access Paper or Ask Questions

Reinforcement Learning for Solving the Vehicle Routing Problem


May 21, 2018
Mohammadreza Nazari, Afshin Oroojlooy, Lawrence V. Snyder, Martin Takáč

* more results and illustrations 

  Access Paper or Ask Questions

Active Metric Learning for Supervised Classification


Mar 28, 2018
Krishnan Kumaran, Dimitri Papageorgiou, Yutong Chang, Minhan Li, Martin Takáč


  Access Paper or Ask Questions

A Deep Q-Network for the Beer Game: A Reinforcement Learning algorithm to Solve Inventory Optimization Problems


Mar 08, 2018
Afshin Oroojlooyjadid, MohammadReza Nazari, Lawrence Snyder, Martin Takáč


  Access Paper or Ask Questions

Stock-out Prediction in Multi-echelon Networks


Mar 08, 2018
Afshin Oroojlooyjadid, Lawrence Snyder, Martin Takáč


  Access Paper or Ask Questions

Applying Deep Learning to the Newsvendor Problem


Mar 06, 2018
Afshin Oroojlooyjadid, Lawrence Snyder, Martin Takáč


  Access Paper or Ask Questions

An Accelerated Communication-Efficient Primal-Dual Optimization Framework for Structured Machine Learning


Nov 14, 2017
Chenxin Ma, Martin Jaggi, Frank E. Curtis, Nathan Srebro, Martin Takáč


  Access Paper or Ask Questions

Underestimate Sequences via Quadratic Averaging


Oct 10, 2017
Chenxin Ma, Naga Venkata C. Gudapati, Majid Jahani, Rachael Tappenden, Martin Takáč


  Access Paper or Ask Questions

A Robust Multi-Batch L-BFGS Method for Machine Learning


Jul 26, 2017
Albert S. Berahas, Martin Takáč

* 47 pages, 26 figures. Extension of NIPS 2016 paper: arXiv:1605.06049 

  Access Paper or Ask Questions

Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory


Jun 06, 2017
Peter Richtárik, Martin Takáč

* 39 pages, 4 reformulations, 3 algorithms 

  Access Paper or Ask Questions

SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient


Jun 03, 2017
Lam M. Nguyen, Jie Liu, Katya Scheinberg, Martin Takáč

* Proceedings of the 34th International Conference on Machine Learning, PMLR 70:2613-2621, 2017 

  Access Paper or Ask Questions

Stochastic Recursive Gradient Algorithm for Nonconvex Optimization


May 20, 2017
Lam M. Nguyen, Jie Liu, Katya Scheinberg, Martin Takáč


  Access Paper or Ask Questions