Martin Takáč
TitleCited byYear
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
P Richtárik, M Takáč
Mathematical Programming 144 (1-2), 1-38, 2014
5812014
Parallel coordinate descent methods for big data optimization
P Richtárik, M Takáč
Mathematical Programming, Series A, 1-52, 2015
3862015
Communication-efficient distributed dual coordinate ascent
M Jaggi, V Smith, M Takác, J Terhorst, S Krishnan, T Hofmann, MI Jordan
Advances in neural information processing systems, 3068-3076, 2014
2382014
Mini-batch semi-stochastic gradient descent in the proximal setting
J Konečný, J Liu, P Richtárik, M Takáč
IEEE Journal of Selected Topics in Signal Processing 10 (2), 242-255, 2015
175*2015
Mini-batch primal and dual methods for SVMs
M Takáč, A Bijral, P Richtárik, N Srebro
In 30th International Conference on Machine Learning, ICML 2013, 2013
168*2013
Distributed coordinate descent method for learning with big data
P Richtárik, M Takác
Journal of Machine Learning Research 17, 1-25, 2016
1622016
SARAH: A novel method for machine learning problems using stochastic recursive gradient
L Nguyen, J Liu, K Scheinberg, M Takáč
In 34th International Conference on Machine Learning, ICML 2017, 2017
1272017
Adding vs. averaging in distributed primal-dual optimization
C Ma, V Smith, M Jaggi, MI Jordan, P Richtárik, M Takáč
arXiv preprint arXiv:1502.03508, 2015
1222015
Adding vs. averaging in distributed primal-dual optimization
C Ma, V Smith, M Jaggi, MI Jordan, P Richtárik, M Takáč
In 32nd International Conference on Machine Learning, ICML 2015, 2015
1222015
CoCoA: A general framework for communication-efficient distributed optimization
V Smith, S Forte, C Ma, M Takáč, MI Jordan, M Jaggi
The Journal of Machine Learning Research 18 (1), 8590-8638, 2017
882017
On optimal probabilities in stochastic coordinate descent methods
P Richtárik, M Takáč
Optimization Letters, 2015, 1-11, 2015
822015
SDNA: stochastic dual newton ascent for empirical risk minimization
Z Qu, P Richtárik, M Takáč, O Fercoq
In 33rd International Conference on Machine Learning, ICML 2016, 2016
642016
Fast distributed coordinate descent for non-strongly convex losses
O Fercoq, Z Qu, P Richtárik, M Takáč
IEEE Workshop on Machine Learning for Signal Processing, 2014, 2014
542014
Distributed optimization with arbitrary local solvers
C Ma, J Konečný, M Jaggi, V Smith, MI Jordan, P Richtárik, M Takáč
Optimization Methods and Software 32 (4), 813-848, 2017
522017
Efficient serial and parallel coordinate descent methods for huge-scale truss topology design
P Richtárik, M Takáč
Operations Research Proceedings 2011, 27-32, 2012
512012
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
LM Nguyen, PH Nguyen, M van Dijk, P Richtárik, K Scheinberg, M Takáč
In 34th International Conference on Machine Learning, ICML 2018, 2018
482018
Distributed block coordinate descent for minimizing partially separable functions
J Marecek, P Richtárik, M Takac
Numerical Analysis and Optimization 2014, Springer Proceedings in …, 2014
482014
A Multi-Batch L-BFGS Method for Machine Learning
AS Berahas, J Nocedal, M Takáč
The Thirtieth Annual Conference on Neural Information Processing Systems (NIPS), 2016
472016
Reinforcement learning for solving the vehicle routing problem
M Nazari, A Oroojlooy, L Snyder, M Takác
Advances in Neural Information Processing Systems, 9839-9849, 2018
462018
Stochastic recursive gradient algorithm for nonconvex optimization
LM Nguyen, J Liu, K Scheinberg, M Takáč
arXiv preprint arXiv:1705.07261, 2017
442017
The system can't perform the operation now. Try again later.
Articles 1–20