Articles with public access mandates - Peter RichtarikLearn more
Available somewhere: 43
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
P Richtarik, M Takáč
Mathematical Programming 144 (2), 1-38, 2014
Mandates: UK Engineering and Physical Sciences Research Council
Parallel coordinate descent methods for big data optimization
P Richtárik, M Takáč
Mathematical Programming 156 (1), 433-484, 2016
Mandates: UK Engineering and Physical Sciences Research Council
SGD: General Analysis and Improved Rates
RM Gower, N Loizou, X Qian, A Sailanbayev, E Shulgin, P Richtarik
ICML 2019, 2019
Mandates: Agence Nationale de la Recherche
Accelerated, parallel and proximal coordinate descent
O Fercoq, P Richtárik
SIAM Journal on Optimization 25 (4), 1997-2023, 2015
Mandates: UK Engineering and Physical Sciences Research Council
Randomized iterative methods for linear systems
RM Gower, P Richtárik
SIAM Journal on Matrix Analysis and Applications 36 (4), 1660-1690, 2015
Mandates: UK Engineering and Physical Sciences Research Council
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, 2016
Mandates: UK Engineering and Physical Sciences Research Council
Semi-stochastic gradient descent methods
J Konečný, P Richtárik
Frontiers in Applied Mathematics and Statistics 3:9, 2017
Mandates: UK Engineering and Physical Sciences Research Council
Distributed coordinate descent method for learning with big data
P Richtárik, M Takáč
Journal of Machine Learning Research 17 (75), 1-25, 2016
Mandates: UK Engineering and Physical Sciences Research Council
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
LM Nguyen, PH Nguyen, M van Dijk, P Richtárik, K Scheinberg, M Takáč
Proceedings of the 35th Int. Conf. on Machine Learning, PMLR 80, 3750-3758, 2018
Mandates: US National Science Foundation, US Department of Defense
Even faster accelerated coordinate descent using non-uniform sampling
Z Allen-Zhu, Z Qu, P Richtarik, Y Yuan
Proceedings of The 33rd Int. Conf. on Machine Learning, PMLR 48, 1110-1119, 2016
Mandates: UK Engineering and Physical Sciences Research Council
Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications
A Chambolle, MJ Ehrhardt, P Richtárik, CB Schönlieb
SIAM Journal on Optimization 28 (4), 2783-2808, 2018
Mandates: Austrian Science Fund, UK Engineering and Physical Sciences Research Council …
Stochastic distributed learning with gradient quantization and double-variance reduction
S Horváth, D Kovalev, K Mishchenko, P Richtárik, S Stich
Optimization Methods and Software 38 (1), 91-106, 2023
Mandates: Swiss National Science Foundation, Helmholtz Association
Stochastic block BFGS: squeezing more curvature out of data
RM Gower, D Goldfarb, P Richtárik
Proceedings of The 33rd Int. Conf. on Machine Learning, PMLR 48, 1869-1878, 2016
Mandates: US National Science Foundation, UK Engineering and Physical Sciences …
Proxskip: Yes! local gradient steps provably lead to communication acceleration! finally!
K Mishchenko, G Malinovsky, S Stich, P Richtárik
International Conference on Machine Learning, 15750-15769, 2022
Mandates: Agence Nationale de la Recherche
Coordinate descent with arbitrary sampling I: algorithms and complexity
Z Qu, P Richtárik
Optimization Methods and Software 31 (5), 829-857, 2016
Mandates: UK Engineering and Physical Sciences Research Council
On optimal probabilities in stochastic coordinate descent methods
P Richtárik, M Takáč
Optimization Letters 10 (6), 1233-1243, 2016
Mandates: UK Engineering and Physical Sciences Research Council
Importance sampling for minibatches
D Csiba, P Richtárik
Journal of Machine Learning Research 19 (27), 1-21, 2018
Mandates: UK Engineering and Physical Sciences Research Council
Stochastic quasi-gradient methods: Variance reduction via Jacobian sketching
RM Gower, P Richtárik, F Bach
Mathematical Programming, 2020 [arXiv preprint arXiv:1805.02632], 2020
Mandates: European Commission
SDNA: stochastic dual Newton ascent for empirical risk minimization
Z Qu, P Richtárik, M Takáč, O Fercoq
Proceedings of the 33rd Int. Conf. on Machine Learning, PMLR 48, 1823-1832, 2016
Mandates: UK Engineering and Physical Sciences Research Council
Randomized distributed mean estimation: Accuracy vs. communication
J Konečný, P Richtárik
Frontiers in Applied Mathematics and Statistics 4, 62, 2018
Mandates: UK Engineering and Physical Sciences Research Council
Publication and funding information is determined automatically by a computer program