All papers are listed below in reverse chronological order in which they appeared online.

Prepared in 2018

Nonconvex variance reduced optimization with arbitrary sampling
Samuel Horváth and Peter Richtárik
Horváth: Best DS3 Poster Award, Data Science Summer School, École Polytechnique, Paris, 2018
[poster] [code: SVRG, SAGA, SARAH]

[79] Accelerated Bregman proximal gradient methods for relatively smooth convex optimization
Filip Hanzely, Peter Richtárik and Lin Xiao
August 2018
[code: ABPG, ABDA]

[78] Matrix completion under interval uncertainty: highlights
Jakub Mareček, Peter Richtárik and Martin Takáč
to appear in: Lecture Notes in Computer Science, ECML-PKDD 2018

[77] Accelerated gossip via stochastic heavy ball method
Nicolas Loizou and Peter Richtárik
to appear in: 56th Annual Allerton Conference on Communication, Control, and Computing, 2018
[poster]

[76] Improving SAGA via a probabilistic interpolation with gradient descent
Adel Bibi, Alibek Sailanbayev, Bernard Ghanem, Robert Mansel Gower and Peter Richtárik
June 2018
[code: SAGD]

[75] A nonconvex projection method for robust PCA
Aritra Dutta, Filip Hanzely and Peter Richtárik
May 2018

[74] Stochastic quasi-gradient methods: variance reduction via Jacobian sketching
Robert M. Gower, Peter Richtárik and Francis Bach
April 2018
[slides] [code: JacSketch]

[73] Weighted low-rank approximation of matrices and background modeling
Aritra Dutta, Xin Li and Peter Richtárik
April 2018

[72] Fastest rates for stochastic mirror descent methods
Filip Hanzely and Peter Richtárik
March 2018

[71] SGD and Hogwild! convergence without the bounded gradients assumption
Lam M. Nguyen, Phuong Ha Nguyen, Marten van Dijk, Peter Richtárik, Katya Scheinberg and Martin Takáč
In Proceedings of The 35th International Conference on Machine Learning, 2018

[70] Accelerated stochastic matrix inversion: general theory and speeding up BFGS rules for faster second-order optimization
Robert M. Gower, Filip Hanzely, Peter Richtárik and Sebastian Stich
February 2018
[code: ABFGS]

[69] Randomized block cubic Newton method
Nikita Doikov and Peter Richtárik
In Proceedings of The 35th International Conference on Machine Learning, 2018
Doikov: Best Talk Award, "Control, Information and Optimization", Voronovo, Russia, 2018
[code: RBCN]

[68] Stochastic spectral and conjugate descent methods
Dmitry Kovalev, Eduard Gorbunov, Elnur Gasanov and Peter Richtárik
February 2018
[poster] [code: SSD, SconD, SSCD, mSSCD, iSconD, iSSD]

[67] A randomized exchange algorithm for computing optimal approximate designs of experiments
Radoslav Harman, Lenka Filová and Peter Richtárik
January 2018
[code: REX, OD_REX, MVEE_REX]

[66] Randomized projection methods for convex feasibility problems: conditioning and convergence rates
Ion Necoara, Andrei Patrascu and Peter Richtárik
January 2018
[slides]

Prepared in 2017

[65] Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods
Nicolas Loizou and Peter Richtárik
December 2017

[64] Online and batch supervised background estimation via L1 regression
Aritra Dutta and Peter Richtárik
November 2017

[63] Linearly convergent stochastic heavy ball method for minimizing generalization error
Nicolas Loizou and Peter Richtárik
In NIPS Workshop on Optimization for Machine Learning, 2017
[poster]

[62] Global convergence of arbitrary-block gradient methods for generalized Polyak-Łojasiewicz functions
Dominik Csiba and Peter Richtárik
to appear in: Mathematical Programming

[61] The complexity of primal-dual fixed point methods for ridge regression
Ademir Alves Ribeiro and Peter Richtárik
Linear Algebra and its Applications 556, 342-372, 2018

[60] Faster PET reconstruction with a stochastic primal-dual hybrid gradient method
Matthias J. Ehrhardt, Pawel Markiewicz, Antonin Chambolle, Peter Richtárik, Jonathan Schott and Carola-Bibiane Schoenlieb
In Proceedings of SPIE, Wavelets and Sparsity XVII, Volume 10394, pages 1039410-1 - 1039410-11, 2017
[poster] [code: SPDHG] YouTube

[59] A batch-incremental video background estimation model using weighted low-rank approximation of matrices
Aritra Dutta, Xin Li and Peter Richtárik
IEEE International Conference on Computer Vision (ICCV) Workshops, 2017
[code: inWLR]

[58] Privacy preserving randomized gossip algorithms
Filip Hanzely, Jakub Konečný, Nicolas Loizou, Peter Richtárik and Dmitry Grishchenko
Preprint, June 2017
[slides]

[57] Stochastic primal-dual hybrid gradient algorithm with arbitrary sampling and imaging applications
Antonin Chambolle, Matthias J. Ehrhardt, Peter Richtárik and Carola-Bibiane Schoenlieb
to appear in: SIAM Journal on Optimization
[slides] [poster] [code: SPDHG] YouTube

[56] Stochastic reformulations of linear systems: algorithms and convergence theory
Peter Richtárik and Martin Takáč
Preprint, June 2017
[slides] [code: basic, parallel and accelerated methods]

[55] Parallel stochastic Newton method
Mojmír Mutný and Peter Richtárik
Journal of Computational Mathematics 36(3):404-425, 2018
[code: PSNM]


Prepared in 2016

[54] Linearly convergent randomized iterative methods for computing the pseudoinverse
Robert M. Gower and Peter Richtárik
Preprint, December 2016

[53] Randomized distributed mean estimation: accuracy vs communication
Jakub Konečný and Peter Richtárik
Preprint, November 2016
Federated Learning Paper

[52] Federated learning: strategies for improving communication efficiency
Jakub Konečný, H. Brendan McMahan, Felix Yu, Peter Richtárik, Ananda Theertha Suresh and Dave Bacon
In NIPS Private Multi-Party Machine Learning Workshop, 2016
Federated Learning Paper link [selected press coverage: The Verge - Quartz - Vice CBR - Android Authority]
[poster]

[51] Federated optimization: distributed machine learning for on-device intelligence
Jakub Konečný, H. Brendan McMahan, Daniel Ramage and Peter Richtárik
Preprint, October 2016
Federated Learning Paper link [selected press coverage: The Verge - Quartz - Vice CBR - Android Authority]

[50] A new perspective on randomized gossip algorithms
Nicolas Loizou and Peter Richtárik
IEEE Global Conference on Signal and Information Processing (GlobalSIP), 440-444, 2016

[49] AIDE: fast and communication efficient distributed optimization
Sashank J. Reddi, Jakub Konečný, Peter Richtárik, Barnabás Póczos, Alex Smola
Preprint, June 2016
[poster]

[48] Coordinate descent face-off: primal or dual?
Dominik Csiba and Peter Richtárik
JMLR Workshop and Conference Proceedings, The 29th International Conference on Algorithmic Learning Theory, 2018

[47] Optimization in high dimensions via accelerated, parallel and proximal coordinate descent
Olivier Fercoq and Peter Richtárik
SIAM Review 58(4), 739-771, 2016
SIAM SIGEST Award

[46] Stochastic block BFGS: squeezing more curvature out of data
Robert M. Gower, Donald Goldfarb and Peter Richtárik
In Proceedings of The 33rd International Conference on Machine Learning, 1869-1878, 2016
[poster]

[45] Importance sampling for minibatches
Dominik Csiba and Peter Richtárik
to appear in: Journal of Machine Learning Research, 2018

[44] Randomized quasi-Newton updates are linearly convergent matrix inversion algorithms
Robert M. Gower and Peter Richtárik
SIAM Journal on Matrix Analysis and Applications 38(4), 1380-1409, 2017
Most Downloaded SIMAX Paper (7th place: 2018)
[code: SIMI, RBFGS, AdaRBFGS, ...]


Prepared in 2015

[43] Even faster accelerated coordinate descent using non-uniform sampling
Zeyuan Allen-Zhu, Zheng Qu, Peter Richtárik and Yang Yuan
In Proceedings of The 33rd International Conference on Machine Learning, 1110-1119, 2016
[code: NU_ACDM]

[42] Stochastic dual ascent for solving linear systems
Robert M. Gower and Peter Richtárik
Preprint, December 2015
[code: SDA] YouTube

[41] Distributed optimization with arbitrary local solvers
Chenxin Ma, Jakub Konečný, Martin Jaggi, Virginia Smith, Michael I Jordan, Peter Richtárik and Martin Takáč
Optimization Methods and Software 32(4), 813-848, 2017
Most-Read Paper, Optimization Methods and Software, 2017
[code: CoCoA+]

[40] Distributed mini-batch SDCA
Martin Takáč, Peter Richtárik and Nathan Srebro
to appear in: Journal of Machine Learning Research, 2018

[39] Randomized iterative methods for linear systems
Robert M. Gower and Peter Richtárik
SIAM Journal on Matrix Analysis and Applications 36(4), 1660-1690, 2015
Most Downloaded SIMAX Paper (1st place: 2017; 2nd place: 2018)

Gower: 18th IMA Leslie Fox Prize (2nd Prize), 2017
link
[slides]

[38] Primal method for ERM with flexible mini-batching schemes and non-convex losses
Dominik Csiba and Peter Richtárik
Preprint, 2015
[code: dfSDCA]

[37] Mini-batch semi-stochastic gradient descent in the proximal setting
Jakub Konečný, Jie Liu, Peter Richtárik and Martin Takáč
IEEE Journal of Selected Topics in Signal Processing 10(2), 242-255, 2016
[code: mS2GD]

[36] On the complexity of parallel coordinate descent
Rachael Tappenden, Martin Takáč and Peter Richtárik
Optimization Methods and Software 33(2), 372-395, 2018

[35] Stochastic dual coordinate ascent with adaptive probabilities
Dominik Csiba, Zheng Qu and Peter Richtárik
In Proceedings of The 32nd International Conference on Machine Learning, 674-683, 2015
Csiba: Best Contribution Award (2nd Place), Optimization and Big Data 2015
Implemented in Tensor Flow
[poster] [code: AdaSDCA and AdaSDCA+]

[34] Adding vs. averaging in distributed primal-dual optimization
Chenxin Ma, Virginia Smith, Martin Jaggi, Michael I. Jordan, Peter Richtárik and Martin Takáč
In Proceedings of The 32nd International Conference on Machine Learning, 1973-1982, 2015
Smith: 2015 MLconf Industry Impact Student Research Award link
CoCoA+ is now the default linear optimizer in Tensor Flow link
[poster] [code: CoCoA+]

[33] SDNA: Stochastic dual Newton ascent for empirical risk minimization
Zheng Qu, Peter Richtárik, Martin Takáč and Olivier Fercoq
In Proceedings of The 33rd International Conference on Machine Learning, 1823-1832, 2016
[slides] [poster] [code: SDNA]


Prepared in 2014

[32] Coordinate descent with arbitrary sampling II: expected separable overapproximation
Zheng Qu and Peter Richtárik
Optimization Methods and Software 31(5), 858-884, 2016

[31] Coordinate descent with arbitrary sampling I: algorithms and complexity
Zheng Qu and Peter Richtárik
Optimization Methods and Software 31(5), 829-857, 2016
[code: ALPHA]

[30] Semi-stochastic coordinate descent
Jakub Konečný, Zheng Qu and Peter Richtárik
Optimization Methods and Software 32 (5), 993-1005, 2017
[code: S2CD]

[29] Quartz: Randomized dual coordinate ascent with arbitrary sampling
Zheng Qu, Peter Richtárik and Tong Zhang
In Advances in Neural Information Processing Systems 28, 865-873, 2015
[slides] [code: QUARTZ] YouTube

[28] mS2GD: Mini-batch semi-stochastic gradient descent in the proximal setting
Jakub Konečný, Jie Liu, Peter Richtárik and Martin Takáč
In NIPS Workshop on Optimization for Machine Learning, 2014
[poster] [code: mS2GD]

[27] S2CD: Semi-stochastic coordinate descent
Jakub Konečný, Zheng Qu and Peter Richtárik
In NIPS Workshop on Optimization for Machine Learning, 2014
[poster] [code: S2CD]

[26] Simple complexity analysis of simplified direct search
Jakub Konečný and Peter Richtárik
Preprint, 2014
[slides in Slovak] [code: SDS]

[25] Distributed block coordinate descent for minimizing partially separable functions
Jakub Mareček, Peter Richtárik and Martin Takáč
Numerical Analysis and Optimization, Springer Proceedings in Math. and Statistics 134, 261-288, 2015

[24] Fast distributed coordinate descent for minimizing non-strongly convex losses
Olivier Fercoq, Zheng Qu, Peter Richtárik and Martin Takáč
In 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2014
[poster] [code: Hydra^2]

[23] On optimal solutions to planetesimal growth models
Duncan Forgan and Peter Richtárik
Preprint, 2014

[22] Matrix completion under interval uncertainty
Jakub Mareček, Peter Richtárik and Martin Takáč
European Journal of Operational Research 256(1), 35-42, 2017
[code: MACO]


Prepared in 2013

[21] Accelerated, Parallel and PROXimal coordinate descent
Olivier Fercoq and Peter Richtárik
SIAM Journal on Optimization 25(4), 1997-2023, 2015
Fercoq: 17th IMA Leslie Fox Prize (Second Prize), 2015
2nd Most Downloaded SIOPT Paper (Aug 2016 - now)
[poster] [code: APPROX] YouTube

[20] Semi-stochastic gradient descent methods
Jakub Konečný and Peter Richtárik
Frontiers in Applied Mathematics and Statistics, 1-14, 2017
[poster] [slides] [code: S2GD and S2GD+]

[19] On optimal probabilities in stochastic coordinate descent methods
Peter Richtárik and Martin Takáč
Optimization Letters 10(6), 1233-1243, 2016
[poster] [code: NSync]

[18] Distributed coordinate descent method for learning with big data
Peter Richtárik and Martin Takáč
Journal of Machine Learning Research 17(75), 1-25, 2016
[poster] [code: Hydra]

[17] Smooth minimization of nonsmooth functions with parallel coordinate descent methods
Olivier Fercoq and Peter Richtárik
Preprint, 2013
[code: SPCDM]

[16] Separable approximations and decomposition methods for the augmented Lagrangian
Rachael Tappenden, Peter Richtárik and Burak Buke
Optimization Methods and Software 30(3), 643-668, 2015

[15] Inexact coordinate descent: complexity and preconditioning
Rachael Tappenden, Peter Richtárik and Jacek Gondzio
Journal of Optimization Theory and Applications 170(1), 144-176, 2016
[poster] [code: ICD]

[14] TOP-SPIN: TOPic discovery via Sparse Principal component INterference
Martin Takáč, Selin Damla Ahipasaoglu, Ngai-Man Cheung and Peter Richtárik
Preprint, 2013
[poster] [code: TOP-SPIN]

[13] Mini-batch primal and dual methods for SVMs
Martin Takáč, Avleen Bijral, Peter Richtárik and Nathan Srebro
In Proceedings of the 30th International Conference on Machine Learning, 2013 
[poster] [code: minibatch SDCA and minibatch Pegasos]


Prepared in 2012

[12] Alternating maximization: unifying framework for 8 sparse PCA formulations and efficient parallel codes
Peter Richtárik, Martin Takáč and Selin Damla Ahipasaoglu
Preprint, 2012
[code: 24am]

[11] Optimal diagnostic tests for sporadic Creutzfeldt-Jakob disease based on SVM classification of RT-QuIC data
William Hulme, Peter Richtárik, Lynne McGuire and Alison Green
Technical Report, 2012

[10] Parallel coordinate descent methods for big data optimization
Peter Richtárik and Martin Takáč
Mathematical Programming 156(1), 433-484, 2016
Takáč: 16th IMA Leslie Fox Prize (2nd Prize), 2013 link
#1 Top Trending Article in Mathematical Programming Ser A and B (2017) link
[slides] [code: PCDM, AC/DC] YouTube


Prepared in 2011

[9] Efficient serial and parallel coordinate descent methods for huge-scale truss topology design
Peter Richtárik and Martin Takáč
Operations Research Proceedings 2011, 27-32, Springer-Verlag, 2012
[poster]

[8] Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
Peter Richtárik and Martin Takáč
Mathematical Programming 144(2), 1-38, 2014
Best Student Paper (runner-up), INFORMS Computing Society, 2012
[slides]

[7] Efficiency of randomized coordinate descent methods on minimization problems with a composite objective function
Peter Richtárik and Martin Takáč
Proceedings of Signal Processing with Adaptive Sparse Structured Representations, 2011

[6] Finding sparse approximations to extreme eigenvectors: generalized power method for sparse PCA and extensions
Peter Richtárik
Proceedings of Signal Processing with Adaptive Sparse Structured Representations, 2011


Prepared in 2010 or earlier

[5] Approximate level method for nonsmooth convex minimization
Peter Richtárik
Journal of Optimization Theory and Applications 152(2), 334–350, 2012

[4] Generalized power method for sparse principal component analysis
Michel Journée, Yurii Nesterov, Peter Richtárik and Rodolphe Sepulchre
Journal of Machine Learning Research 11, 517–553, 2010
[slides] [poster] [code: GPower]

[3] Improved algorithms for convex minimization in relative scale
Peter Richtárik
SIAM Journal on Optimization 21(3), 1141–1167, 2011
[slides]

[2] Simultaneously solving seven optimization problems in relative scale
Peter Richtárik
Technical Report, 2009

[1] Some algorithms for large-scale convex and linear minimization in relative scale
Peter Richtárik
PhD Dissertation, School of Operations Research and Information Engineering, Cornell University, 2007