| 2025 | ECAI | Quantize Once, Train Fast: Allreduce-Compatible Compression with Provable Guarantees. | Jihao Xin, Marco Canini, Peter Richtrik, Samuel Horvth |
| 2025 | ICLR | LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression. | Laurent Condat, Arto Maranjyan, Peter Richtrik |
| 2025 | ICLR | MAST: model-agnostic sparsified training. | Yury Demidovich, Grigory Malinovsky, Egor Shulgin, Peter Richtrik |
| 2025 | ICLR | Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization. | Yury Demidovich, Petr Ostroukhov, Grigory Malinovsky, Samuel Horvth, Martin Takc, Peter Richtrik, Eduard Gorbunov |
| 2025 | ICLR | Methods for Convex (L0, L1)-Smooth Optimization: Clipping, Acceleration, and Adaptivity. | Eduard Gorbunov, Nazarii Tupitsa, Sayantan Choudhury, Alen Aliev, Peter Richtrik, Samuel Horvth, Martin Takc |
| 2025 | ICML | ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning. | Arto Maranjyan, El Mehdi Saad, Peter Richtrik, Francesco Orabona |
| 2025 | ICML | Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity. | Arto Maranjyan, Alexander Tyurin, Peter Richtrik |
| 2025 | NAACL | HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem. | Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtrik, Dan Alistarh |
| 2025 | UAI | ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression. | Avetik G. Karagulyan, Peter Richtrik |
| 2025 | UAI | MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times. | Arto Maranjyan, Omar Shaikh Omar, Peter Richtrik |
| 2025 | UAI | Correlated Quantization for Faster Nonconvex Distributed Optimization. | Andrei Panferov, Yury Demidovich, Ahmad Rammal, Peter Richtrik |
| 2024 | AAAI | Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization. | Soumia Boucherouite, Grigory Malinovsky, Peter Richtrik, El Houcine Bergou |
| 2024 | AISTATS | Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates. | Ahmad Rammal, Kaja Gruntkowska, Nikita Fedin, Eduard Gorbunov, Peter Richtrik |
| 2024 | AISTATS | Understanding Progressive Training Through the Framework of Randomized Coordinate Descent. | Rafal Szlendak, Elnur Gasanov, Peter Richtrik |
| 2024 | ICLR | Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization. | Hanmin Li, Avetik G. Karagulyan, Peter Richtrik |
| 2024 | ICLR | Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants. | Peter Richtrik, Elnur Gasanov, Konstantin Burlachenko |
| 2024 | ICLR | FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity. | Kai Yi, Nidham Gazagnadou, Peter Richtrik, Lingjuan Lyu |
| 2024 | ICML | High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise. | Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horvth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtrik |
| 2024 | ICML | Towards a Better Theoretical Understanding of Independent Subnetwork Training. | Egor Shulgin, Peter Richtrik |
| 2023 | AISTATS | Can 5th Generation Local Training Methods Support Client Sampling? Yes! | Michal Grudzien, Grigory Malinovsky, Peter Richtrik |
| 2023 | AISTATS | Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity. | Xun Qian, Hanze Dong, Tong Zhang, Peter Richtrik |
| 2023 | AISTATS | Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition. | Lukang Sun, Avetik G. Karagulyan, Peter Richtrik |
| 2023 | ICLR | RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates. | Laurent Condat, Peter Richtrik |
| 2023 | ICLR | Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top. | Eduard Gorbunov, Samuel Horvth, Peter Richtrik, Gauthier Gidel |
| 2023 | ICLR | DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity. | Alexander Tyurin, Peter Richtrik |
| 2023 | ICML | EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression. | Kaja Gruntkowska, Alexander Tyurin, Peter Richtrik |
| 2023 | ICML | High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance. | Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horvth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtrik |
| 2023 | UAI | Random Reshuffling with Variance Reduction: New Analysis and Better Rates. | Grigory Malinovsky, Alibek Sailanbayev, Peter Richtrik |
| 2022 | AISTATS | FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning. | Elnur Gasanov, Ahmed Khaled, Samuel Horvth, Peter Richtrik |
| 2022 | AISTATS | Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning. | Xun Qian, Rustem Islamov, Mher Safaryan, Peter Richtrik |
| 2022 | AISTATS | An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints. | Adil Salim, Laurent Condat, Dmitry Kovalev, Peter Richtrik |
| 2022 | ICLR | Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information. | Majid Jahani, Sergey Rusakov, Zheng Shi, Peter Richtrik, Michael W. Mahoney, Martin Takc |
| 2022 | ICLR | IntSGD: Adaptive Floatless Compression of Stochastic Gradients. | Konstantin Mishchenko, Bokun Wang, Dmitry Kovalev, Peter Richtrik |
| 2022 | ICLR | Permutation Compressors for Provably Faster Distributed Nonconvex Optimization. | Rafal Szlendak, Alexander Tyurin, Peter Richtrik |
| 2022 | ICML | Proximal and Federated Random Reshuffling. | Konstantin Mishchenko, Ahmed Khaled, Peter Richtrik |
| 2022 | ICML | ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! | Konstantin Mishchenko, Grigory Malinovsky, Sebastian U. Stich, Peter Richtrik |
| 2022 | ICML | 3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation. | Peter Richtrik, Igor Sokolov, Elnur Gasanov, Ilyas Fatkhullin, Zhize Li, Eduard Gorbunov |
| 2022 | ICML | FedNL: Making Newton-Type Methods Applicable to Federated Learning. | Mher Safaryan, Rustem Islamov, Xun Qian, Peter Richtrik |
| 2022 | ICML | A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1. | Adil Salim, Lukang Sun, Peter Richtrik |
| 2022 | UAI | Shifted compression framework: generalizations and improvements. | Egor Shulgin, Peter Richtrik |
| 2021 | AISTATS | Local SGD: Unified Theory and New Efficient Methods. | Eduard Gorbunov, Filip Hanzely, Peter Richtrik |
| 2021 | AISTATS | Hyperparameter Transfer Learning with Adaptive Complexity. | Samuel Horvth, Aaron Klein, Peter Richtrik, Cdric Archambeau |
| 2021 | AISTATS | A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! | Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtrik, Sebastian U. Stich |
| 2021 | CoNEXT | FL_PyTorch: optimization research simulator for federated learning. | Konstantin Burlachenko, Samuel Horvth, Peter Richtrik |
| 2021 | ICLR | A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning. | Samuel Horvth, Peter Richtrik |
| 2021 | ICML | MARINA: Faster Non-Convex Distributed Learning with Compression. | Eduard Gorbunov, Konstantin Burlachenko, Zhize Li, Peter Richtrik |
| 2021 | ICML | Distributed Second Order Methods with Fast Rates and Compressed Communication. | Rustem Islamov, Xun Qian, Peter Richtrik |
| 2021 | ICML | ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks. | Dmitry Kovalev, Egor Shulgin, Peter Richtrik, Alexander Rogozin, Alexander V. Gasnikov |
| 2021 | ICML | PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization. | Zhize Li, Hongyan Bao, Xiangliang Zhang, Peter Richtrik |
| 2021 | ICML | Stochastic Sign Descent Methods: New Algorithms and Better Theory. | Mher Safaryan, Peter Richtrik |
| 2021 | NSDI | Scaling Distributed Machine Learning with In-Network Aggregation. | Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan R. K. Ports, Peter Richtrik |
| 2020 | AAAI | A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control. | Adel Bibi, El Houcine Bergou, Ozan Sener, Bernard Ghanem, Peter Richtrik |
| 2020 | AISTATS | Tighter Theory for Local SGD on Identical and Heterogeneous Data. | Ahmed Khaled, Konstantin Mishchenko, Peter Richtrik |
| 2020 | AISTATS | A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent. | Eduard Gorbunov, Filip Hanzely, Peter Richtrik |
| 2020 | AISTATS | Revisiting Stochastic Extragradient. | Konstantin Mishchenko, Dmitry Kovalev, Egor Shulgin, Peter Richtrik, Yura Malitsky |
| 2020 | ALT | Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop. | Dmitry Kovalev, Samuel Horvth, Peter Richtrik |
| 2020 | ICLR | A Stochastic Derivative Free Optimization Method with Momentum. | Eduard Gorbunov, Adel Bibi, Ozan Sener, El Houcine Bergou, Peter Richtrik |
| 2020 | ICML | Stochastic Subspace Cubic Newton Method. | Filip Hanzely, Nikita Doikov, Yurii E. Nesterov, Peter Richtrik |
| 2020 | ICML | Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems. | Filip Hanzely, Dmitry Kovalev, Peter Richtrik |
| 2020 | ICML | Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization. | Zhize Li, Dmitry Kovalev, Xun Qian, Peter Richtrik |
| 2020 | ICML | From Local SGD to Local Fixed-Point Methods for Federated Learning. | Grigory Malinovskiy, Dmitry Kovalev, Elnur Gasanov, Laurent Condat, Peter Richtrik |
| 2020 | UAI | 99% of Worker-Master Communication in Distributed Optimization Is Not Needed. | Konstantin Mishchenko, Filip Hanzely, Peter Richtrik |
| 2019 | AAAI | A Nonconvex Projection Method for Robust PCA. | Aritra Dutta, Filip Hanzely, Peter Richtrik |
| 2019 | AISTATS | Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches. | Filip Hanzely, Peter Richtrik |
| 2019 | ICASSP | Provably Accelerated Randomized Gossip Algorithms. | Nicolas Loizou, Michael G. Rabbat, Peter Richtrik |
| 2019 | ICML | Nonconvex Variance Reduced Optimization with Arbitrary Sampling. | Samuel Horvth, Peter Richtrik |
| 2019 | ICML | SAGA with Arbitrary Sampling. | Xun Qian, Zheng Qu, Peter Richtrik |
| 2019 | ICML | SGD with Arbitrary Sampling: General Analysis and Improved Rates. | Xun Qian, Peter Richtrik, Robert M. Gower, Alibek Sailanbayev, Nicolas Loizou, Egor Shulgin |
| 2019 | WACV | Online and Batch Supervised Background Estimation Via L1 Regression. | Aritra Dutta, Peter Richtrik |
| 2018 | ALT | Coordinate Descent Faceoff: Primal or Dual? | Dominik Csiba, Peter Richtrik |
| 2018 | ICML | Randomized Block Cubic Newton Method. | Nikita Doikov, Peter Richtrik |
| 2018 | ICML | SGD and Hogwild! Convergence Without the Bounded Gradients Assumption. | Lam M. Nguyen, Phuong Ha Nguyen, Marten van Dijk, Peter Richtrik, Katya Scheinberg, Martin Takc |
| 2016 | ICML | Stochastic Block BFGS: Squeezing More Curvature out of Data. | Robert M. Gower, Donald Goldfarb, Peter Richtrik |
| 2016 | ICML | SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization. | Zheng Qu, Peter Richtrik, Martin Takc, Olivier Fercoq |
| 2016 | ICML | Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling. | Zeyuan Allen Zhu, Zheng Qu, Peter Richtrik, Yang Yuan |
| 2015 | ICML | Stochastic Dual Coordinate Ascent with Adaptive Probabilities. | Dominik Csiba, Zheng Qu, Peter Richtrik |
| 2015 | ICML | Adding vs. Averaging in Distributed Primal-Dual Optimization. | Chenxin Ma, Virginia Smith, Martin Jaggi, Michael I. Jordan, Peter Richtrik, Martin Takc |
| 2013 | ICML | Mini-Batch Primal and Dual Methods for SVMs. | Martin Takc, Avleen Singh Bijral, Peter Richtrik, Nati Srebro |