| SGD: General analysis and improved rates RM Gower, N Loizou, X Qian, A Sailanbayev, E Shulgin, P Richtárik Proceedings of the 36 the International Conference on Machine Learning, 2019 | 451 | 2019 |
| Randomized iterative methods for linear systems RM Gower, P Richtárik SIAM Journal on Matrix Analysis and Applications 36 (4), 1660-1690, 2015 | 334 | 2015 |
| Stochastic block BFGS: Squeezing more curvature out of data RM Gower, D Goldfarb, P Richtárik International Conference on Machine Learning, 1869-1878, 2016 | 193 | 2016 |
| Variance-reduced methods for machine learning RM Gower, M Schmidt, F Bach, P Richtárik Proceedings of the IEEE 108 (11), 1968-1983, 2020 | 126 | 2020 |
| Almost sure convergence rates for stochastic gradient descent and stochastic heavy ball O Sebbouh, RM Gower, A Defazio Conference on Learning Theory, 3935-3971, 2021 | 120* | 2021 |
| Stochastic quasi-gradient methods: Variance reduction via Jacobian sketching RM Gower, P Richtárik, F Bach Mathematical Programming, 2020 | 116 | 2020 |
| Handbook of convergence theorems for (stochastic) gradient methods G Garrigos, RM Gower arXiv preprint arXiv:2301.11235, 2023 | 106* | 2023 |
| Randomized quasi-Newton updates are linearly convergent matrix inversion algorithms RM Gower, P Richtárik SIAM Journal on Matrix Analysis and Applications 38 (4), 1380-1409, 2017 | 101 | 2017 |
| RSN: randomized subspace Newton RM Gower, D Kovalev, F Lieder, P Richtárik Advances in Neural Information Processing Systems 32, 2019 | 95 | 2019 |
| Sgd for structured nonconvex functions: Learning rates, minibatching and interpolation RM Gower, O Sebbouh, N Loizou International Conference on Artificial Intelligence and Statistics, 1315-1323, 2021 | 83 | 2021 |
| Stochastic dual ascent for solving linear systems RM Gower, P Richtárik arXiv preprint arXiv:1512.06890, 2015 | 71 | 2015 |
| On adaptive sketch-and-project for solving linear systems RM Gower, D Molitor, J Moorman, D Needell SIAM Journal on Matrix Analysis and Applications 42 (2), 954-989, 2021 | 58* | 2021 |
| A general sample complexity analysis of vanilla policy gradient R Yuan, RM Gower, A Lazaric International Conference on Artificial Intelligence and Statistics, 3332-3380, 2022 | 57 | 2022 |
| Accelerated stochastic matrix inversion: general theory and speeding up BFGS rules for faster second-order optimization RM Gower, F Hanzely, P Richtárik, SU Stich Advances in Neural Information Processing Systems 31, 2018 | 51 | 2018 |
| Unified analysis of stochastic gradient methods for composite convex and smooth optimization A Khaled, O Sebbouh, N Loizou, RM Gower, P Richtárik Journal of Optimization Theory and Applications 199 (2), 499-540, 2023 | 46 | 2023 |
| Optimal mini-batch and step sizes for saga N Gazagnadou, RM Gower, J Salmon International conference on machine learning, 2142-2150, 2019 | 43 | 2019 |
| Linear convergence of natural policy gradient methods with log-linear policies R Yuan, SS Du, RM Gower, A Lazaric, L Xiao arXiv preprint arXiv:2210.01400, 2022 | 35 | 2022 |
| Tracking the gradients using the hessian: A new look at variance reducing stochastic methods RM Gower, N Le Roux, F Bach International Conference on Artificial Intelligence and Statistics, 707-715, 2018 | 34 | 2018 |
| Sketched Newton--Raphson R Yuan, A Lazaric, RM Gower SIAM Journal on Optimization 32 (3), 1555-1583, 2022 | 33* | 2022 |
| Stochastic algorithms for entropy-regularized optimal transport problems BK Abid, RM Gower International Conference on Artificial Intelligence and Statistics, 1505-1512, 2018 | 32 | 2018 |
Peter RichtarikProfessor, KAUSTVerified email at kaust.edu.sa
