default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDPeter Richtárik
Person information
- affiliation: King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
- affiliation (former): University of Edinburgh, UK
- affiliation (former): Moscow Institute of Physics and Technology (MIPT), Dolgoprudny, Russia
- affiliation (former, PhD 2007): Cornell University, Ithaca, NY, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j54]Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtárik
:
Faster Rates for Compressed Federated Learning with Client-Variance Reduction. SIAM J. Math. Data Sci. 6(1): 154-175 (2024)- [j53]Lukang Sun, Adil Salim, Peter Richtárik:
Federated Sampling with Langevin Algorithm under Isoperimetry. Trans. Mach. Learn. Res. 2024 (2024) - [c109]Soumia Boucherouite, Grigory Malinovsky, Peter Richtárik, El Houcine Bergou:
Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization. AAAI 2024: 20344-20352 - [c108]Ahmad Rammal, Kaja Gruntkowska, Nikita Fedin, Eduard Gorbunov, Peter Richtárik:
Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates. AISTATS 2024: 1207-1215 - [c107]Rafal Szlendak, Elnur Gasanov, Peter Richtárik:
Understanding Progressive Training Through the Framework of Randomized Coordinate Descent. AISTATS 2024: 2161-2169 - [c106]Hanmin Li, Avetik G. Karagulyan, Peter Richtárik:
Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization. ICLR 2024 - [c105]Peter Richtárik, Elnur Gasanov, Konstantin Burlachenko:
Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants. ICLR 2024 - [c104]Kai Yi, Nidham Gazagnadou, Peter Richtárik, Lingjuan Lyu:
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity. ICLR 2024 - [c103]Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik:
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise. ICML 2024 - [c102]Egor Shulgin, Peter Richtárik:
Towards a Better Theoretical Understanding of Independent Subnetwork Training. ICML 2024 - [i200]Andrei Panferov, Yury Demidovich, Ahmad Rammal, Peter Richtárik:
Correlated Quantization for Faster Nonconvex Distributed Optimization. CoRR abs/2401.05518 (2024) - [i199]Alexander Tyurin, Marta Pozzi, Ivan Ilin, Peter Richtárik:
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity. CoRR abs/2402.04785 (2024) - [i198]Kaja Gruntkowska, Alexander Tyurin, Peter Richtárik:
Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity. CoRR abs/2402.06412 (2024) - [i197]Peter Richtárik, Elnur Gasanov, Konstantin Burlachenko:
Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants. CoRR abs/2402.10774 (2024) - [i196]Laurent Condat, Artavazd Maranjyan, Peter Richtárik:
LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression. CoRR abs/2403.04348 (2024) - [i195]Yury Demidovich, Grigory Malinovsky, Peter Richtárik:
Streamlining in the Riemannian Realm: Efficient Riemannian Optimization with Loopless Variance Reduction. CoRR abs/2403.06677 (2024) - [i194]Kai Yi, Georg Meinhardt, Laurent Condat, Peter Richtárik:
FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models. CoRR abs/2403.09904 (2024) - [i193]Kai Yi, Nidham Gazagnadou, Peter Richtárik, Lingjuan Lyu:
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity. CoRR abs/2404.09816 (2024) - [i192]Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtárik:
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression. CoRR abs/2405.14852 (2024) - [i191]Alexander Tyurin, Kaja Gruntkowska, Peter Richtárik:
Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations. CoRR abs/2405.15545 (2024) - [i190]Ionut-Vlad Modoranu, Mher Safaryan, Grigory Malinovsky, Eldar Kurtic, Thomas Robert, Peter Richtárik, Dan Alistarh:
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence. CoRR abs/2405.15593 (2024) - [i189]Peter Richtárik, Abdurakhmon Sadiev, Yury Demidovich:
A Unified Theory of Stochastic Proximal Point Methods without Smoothness. CoRR abs/2405.15941 (2024) - [i188]Avetik G. Karagulyan, Egor Shulgin, Abdurakhmon Sadiev, Peter Richtárik:
SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning. CoRR abs/2405.20127 (2024) - [i187]Georg Meinhardt, Kai Yi, Laurent Condat, Peter Richtárik:
Prune at the Clients, Not the Server: Accelerated Sparse Training in Federated Learning. CoRR abs/2405.20623 (2024) - [i186]Kai Yi, Timur Kharisov, Igor Sokolov, Peter Richtárik:
Cohort Squeeze: Beyond a Single Communication Round per Cohort in Cross-Device Federated Learning. CoRR abs/2406.01115 (2024) - [i185]Eduard Gorbunov, Nazarii Tupitsa, Sayantan Choudhury, Alen Aliev, Peter Richtárik, Samuel Horváth, Martin Takác:
Methods for Convex (L0,L1)-Smooth Optimization: Clipping, Acceleration, and Adaptivity. CoRR abs/2409.14989 (2024) - [i184]Hanmin Li, Peter Richtárik:
On the Convergence of FedProx with Extrapolation and Inexact Prox. CoRR abs/2410.01410 (2024) - [i183]Artavazd Maranjyan, Omar Shaikh Omar, Peter Richtárik:
MindFlayer: Efficient Asynchronous Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times. CoRR abs/2410.04285 (2024) - [i182]Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud, Taha Ceritli, Hayder Elesedy, Mete Ozay, Peter Richtárik:
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation. CoRR abs/2410.08305 (2024) - [i181]Konstantin Burlachenko, Peter Richtárik:
Unlocking FedNL: Self-Contained Compute-Optimized Implementation. CoRR abs/2410.08760 (2024) - [i180]Wojciech Anyszka, Kaja Gruntkowska, Alexander Tyurin, Peter Richtárik:
Tighter Performance Theory of FedExProx. CoRR abs/2410.15368 (2024) - [i179]Sarit Khirirat, Abdurakhmon Sadiev, Artem Riabinin, Eduard Gorbunov, Peter Richtárik:
Error Feedback under (L0,L1)-Smoothness: Normalization and Momentum. CoRR abs/2410.16871 (2024) - [i178]Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtárik, Dan Alistarh:
Pushing the Limits of Large Language Model Quantization via the Linearity Theorem. CoRR abs/2411.17525 (2024) - 2023
- [j52]Aleksandr Beznosikov, Samuel Horváth, Peter Richtárik, Mher Safaryan:
On Biased Compression for Distributed Learning. J. Mach. Learn. Res. 24: 276:1-276:50 (2023) - [j51]Ahmed Khaled, Othmane Sebbouh, Nicolas Loizou, Robert M. Gower, Peter Richtárik:
Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization. J. Optim. Theory Appl. 199(2): 499-540 (2023) - [j50]Samuel Horváth, Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik, Sebastian U. Stich:
Stochastic distributed learning with gradient quantization and double-variance reduction. Optim. Methods Softw. 38(1): 91-106 (2023) - [j49]El Houcine Bergou, Konstantin Burlachenko, Aritra Dutta, Peter Richtárik:
Personalized Federated Learning with Communication Compression. Trans. Mach. Learn. Res. 2023 (2023) - [j48]Rustem Islamov, Xun Qian, Slavomír Hanzely, Mher Safaryan, Peter Richtárik:
Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation. Trans. Mach. Learn. Res. 2023 (2023) - [j47]Ahmed Khaled, Peter Richtárik:
Better Theory for SGD in the Nonconvex World. Trans. Mach. Learn. Res. 2023 (2023) - [j46]Maksim Makarenko, Elnur Gasanov, Abdurakhmon Sadiev, Rustem Islamov, Peter Richtárik:
Adaptive Compression for Communication-Efficient Distributed Training. Trans. Mach. Learn. Res. 2023 (2023) - [j45]Zheng Shi, Abdurakhmon Sadiev, Nicolas Loizou, Peter Richtárik, Martin Takác:
AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods. Trans. Mach. Learn. Res. 2023 (2023) - [j44]Alexander Tyurin, Lukang Sun, Konstantin Burlachenko, Peter Richtárik:
Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling. Trans. Mach. Learn. Res. 2023 (2023) - [c101]Xun Qian, Hanze Dong, Tong Zhang, Peter Richtárik:
Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity. AISTATS 2023: 615-649 - [c100]Michal Grudzien, Grigory Malinovsky, Peter Richtárik:
Can 5th Generation Local Training Methods Support Client Sampling? Yes! AISTATS 2023: 1055-1092 - [c99]Lukang Sun, Avetik G. Karagulyan, Peter Richtárik:
Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition. AISTATS 2023: 3693-3717 - [c98]Jihao Xin, Ivan Ilin, Shunkang Zhang, Marco Canini, Peter Richtárik:
Kimad: Adaptive Gradient Compression with Bandwidth Awareness. DistributedML@CoNEXT 2023: 35-48 - [c97]Konstantin Burlachenko, Abdulmajeed Alrowithi, Fahad Ali Albalawi, Peter Richtárik:
Federated Learning is Better with Non-Homomorphic Encryption. DistributedML@CoNEXT 2023: 49-84 - [c96]Grigory Malinovsky, Konstantin Mishchenko, Peter Richtárik:
Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization. DistributedML@CoNEXT 2023: 85-104 - [c95]Laurent Condat, Peter Richtárik:
RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates. ICLR 2023 - [c94]Eduard Gorbunov, Samuel Horváth, Peter Richtárik, Gauthier Gidel:
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top. ICLR 2023 - [c93]Alexander Tyurin, Peter Richtárik:
DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity. ICLR 2023 - [c92]Kaja Gruntkowska, Alexander Tyurin, Peter Richtárik:
EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression. ICML 2023: 11761-11807 - [c91]Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik:
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance. ICML 2023: 29563-29648 - [c90]Yury Demidovich, Grigory Malinovsky, Igor Sokolov, Peter Richtárik:
A Guide Through the Zoo of Biased SGD. NeurIPS 2023 - [c89]Ilyas Fatkhullin, Alexander Tyurin, Peter Richtárik:
Momentum Provably Improves Error Feedback! NeurIPS 2023 - [c88]Alexander Tyurin, Peter Richtárik:
2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression. NeurIPS 2023 - [c87]Alexander Tyurin, Peter Richtárik:
Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model. NeurIPS 2023 - [c86]Alexander Tyurin, Peter Richtárik:
A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting. NeurIPS 2023 - [c85]Grigory Malinovsky, Alibek Sailanbayev, Peter Richtárik:
Random Reshuffling with Variance Reduction: New Analysis and Better Rates. UAI 2023: 1347-1357 - [i177]Konstantin Mishchenko, Slavomír Hanzely, Peter Richtárik:
Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes. CoRR abs/2301.06806 (2023) - [i176]Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik:
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance. CoRR abs/2302.00999 (2023) - [i175]Grigory Malinovsky, Samuel Horváth, Konstantin Burlachenko, Peter Richtárik:
Federated Learning with Regularized Client Participation. CoRR abs/2302.03662 (2023) - [i174]Laurent Condat, Grigory Malinovsky, Peter Richtárik:
TAMUNA: Accelerated Federated Learning with Local Training and Partial Participation. CoRR abs/2302.09832 (2023) - [i173]Avetik G. Karagulyan, Peter Richtárik:
ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression. CoRR abs/2303.04622 (2023) - [i172]Kai Yi, Laurent Condat, Peter Richtárik:
Explicit Personalization and Local Training: Double Communication Acceleration in Federated Learning. CoRR abs/2305.13170 (2023) - [i171]Ilyas Fatkhullin, Alexander Tyurin, Peter Richtárik:
Momentum Provably Improves Error Feedback! CoRR abs/2305.15155 (2023) - [i170]Peter Richtárik, Elnur Gasanov, Konstantin Burlachenko:
Error Feedback Shines when Features are Rare. CoRR abs/2305.15264 (2023) - [i169]Yury Demidovich, Grigory Malinovsky, Igor Sokolov, Peter Richtárik:
A Guide Through the Zoo of Biased SGD. CoRR abs/2305.16296 (2023) - [i168]Jihao Xin, Marco Canini, Peter Richtárik, Samuel Horváth:
Global-QSGD: Practical Floatless Quantization for Distributed Learning with Theoretical Guarantees. CoRR abs/2305.18627 (2023) - [i167]Sarit Khirirat, Eduard Gorbunov, Samuel Horváth, Rustem Islamov, Fakhri Karray, Peter Richtárik:
Clip21: Error Feedback for Gradient Clipping. CoRR abs/2305.18929 (2023) - [i166]Michal Grudzien, Grigory Malinovsky, Peter Richtárik:
Improving Accelerated Federated Learning with Compression and Importance Sampling. CoRR abs/2306.03240 (2023) - [i165]Rafal Szlendak, Elnur Gasanov, Peter Richtárik:
Understanding Progressive Training Through the Framework of Randomized Coordinate Descent. CoRR abs/2306.03626 (2023) - [i164]Egor Shulgin, Peter Richtárik:
Towards a Better Theoretical Understanding of Independent Subnetwork Training. CoRR abs/2306.16484 (2023) - [i163]Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik:
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise. CoRR abs/2310.01860 (2023) - [i162]Ahmad Rammal, Kaja Gruntkowska, Nikita Fedin, Eduard Gorbunov, Peter Richtárik:
Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates. CoRR abs/2310.09804 (2023) - [i161]Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov:
Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences. CoRR abs/2311.14127 (2023) - [i160]Yury Demidovich, Grigory Malinovsky, Egor Shulgin, Peter Richtárik:
MAST: Model-Agnostic Sparsified Training. CoRR abs/2311.16086 (2023) - [i159]Konstantin Burlachenko, Abdulmajeed Alrowithi, Fahad Ali Albalawi, Peter Richtárik:
Federated Learning is Better with Non-Homomorphic Encryption. CoRR abs/2312.02074 (2023) - [i158]Jihao Xin, Ivan Ilin, Shunkang Zhang, Marco Canini, Peter Richtárik:
Kimad: Adaptive Gradient Compression with Bandwidth Awareness. CoRR abs/2312.08053 (2023) - 2022
- [j43]Aritra Dutta, El Houcine Bergou, Yunming Xiao, Marco Canini, Peter Richtárik:
Direct nonlinear acceleration. EURO J. Comput. Optim. 10: 100047 (2022) - [j42]Adil Salim, Laurent Condat, Konstantin Mishchenko, Peter Richtárik:
Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms. J. Optim. Theory Appl. 195(1): 102-130 (2022) - [j41]Albert S. Berahas, Majid Jahani, Peter Richtárik, Martin Takác:
Quasi-Newton methods for machine learning: forget the past, just sample. Optim. Methods Softw. 37(5): 1668-1704 (2022) - [j40]Samuel Horváth, Lihua Lei, Peter Richtárik, Michael I. Jordan:
Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization. SIAM J. Math. Data Sci. 4(2): 634-648 (2022) - [j39]Wenlin Chen, Samuel Horváth, Peter Richtárik:
Optimal Client Sampling for Federated Learning. Trans. Mach. Learn. Res. 2022 (2022) - [j38]Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik, Michael G. Rabbat:
FedShuffle: Recipes for Better Use of Local Work in Federated Learning. Trans. Mach. Learn. Res. 2022 (2022) - [c84]Xun Qian, Rustem Islamov, Mher Safaryan, Peter Richtárik:
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning. AISTATS 2022: 680-720 - [c83]Adil Salim, Laurent Condat, Dmitry Kovalev, Peter Richtárik:
An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints. AISTATS 2022: 4482-4498 - [c82]Elnur Gasanov, Ahmed Khaled, Samuel Horváth, Peter Richtárik:
FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning. AISTATS 2022: 11374-11421 - [c81]Majid Jahani, Sergey Rusakov, Zheng Shi, Peter Richtárik, Michael W. Mahoney, Martin Takác:
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information. ICLR 2022 - [c80]Konstantin Mishchenko, Bokun Wang, Dmitry Kovalev, Peter Richtárik:
IntSGD: Adaptive Floatless Compression of Stochastic Gradients. ICLR 2022 - [c79]Rafal Szlendak, Alexander Tyurin, Peter Richtárik:
Permutation Compressors for Provably Faster Distributed Nonconvex Optimization. ICLR 2022 - [c78]Konstantin Mishchenko, Ahmed Khaled, Peter Richtárik:
Proximal and Federated Random Reshuffling. ICML 2022: 15718-15749 - [c77]Konstantin Mishchenko, Grigory Malinovsky, Sebastian U. Stich, Peter Richtárik:
ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! ICML 2022: 15750-15769 - [c76]Peter Richtárik, Igor Sokolov, Elnur Gasanov, Ilyas Fatkhullin, Zhize Li, Eduard Gorbunov:
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation. ICML 2022: 18596-18648 - [c75]Mher Safaryan, Rustem Islamov, Xun Qian, Peter Richtárik:
FedNL: Making Newton-Type Methods Applicable to Federated Learning. ICML 2022: 18959-19010 - [c74]Adil Salim, Lukang Sun, Peter Richtárik:
A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1. ICML 2022: 19139-19152 - [c73]Laurent Condat, Peter Richtárik:
MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization. MSML 2022: 81-96 - [c72]Samuel Horváth, Chen-Yu Ho, Ludovit Horvath, Atal Narayan Sahu, Marco Canini, Peter Richtárik:
Natural Compression for Distributed Deep Learning. MSML 2022: 129-141 - [c71]Aleksandr Beznosikov, Peter Richtárik, Michael Diskin, Max Ryabinin, Alexander V. Gasnikov:
Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees. NeurIPS 2022 - [c70]Laurent Condat, Kai Yi, Peter Richtárik:
EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization. NeurIPS 2022 - [c69]Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander V. Gasnikov, Peter Richtárik, Martin Takác:
A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate. NeurIPS 2022 - [c68]Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander V. Gasnikov:
Optimal Algorithms for Decentralized Stochastic Variational Inequalities. NeurIPS 2022 - [c67]Dmitry Kovalev, Alexander V. Gasnikov, Peter Richtárik:
Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling. NeurIPS 2022 - [c66]Grigory Malinovsky, Kai Yi, Peter Richtárik:
Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning. NeurIPS 2022 - [c65]Abdurakhmon Sadiev, Dmitry Kovalev, Peter Richtárik:
Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with an Inexact Prox. NeurIPS 2022 - [c64]Bokun Wang, Mher Safaryan, Peter Richtárik:
Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques. NeurIPS 2022 - [c63]Haoyu Zhao, Boyue Li, Zhize Li, Peter Richtárik, Yuejie Chi:
BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression. NeurIPS 2022 - [c62]Egor Shulgin, Peter Richtárik:
Shifted compression framework: generalizations and improvements. UAI 2022: 1813-1823 - [i157]Grigory Malinovsky, Konstantin Mishchenko, Peter Richtárik:
Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization. CoRR abs/2201.11066 (2022) - [i156]Haoyu Zhao, Boyue Li, Zhize Li, Peter Richtárik, Yuejie Chi:
BEER: Fast O(1/T) Rate for Decentralized Nonconvex Optimization with Communication Compression. CoRR abs/2201.13320 (2022) - [i155]Peter Richtárik, Igor Sokolov, Ilyas Fatkhullin, Elnur Gasanov, Zhize Li, Eduard Gorbunov:
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation. CoRR abs/2202.00998 (2022) - [i154]Alexander Tyurin, Peter Richtárik:
DASHA: Distributed Nonconvex Optimization with Communication Compression, Optimal Oracle Complexity, and No Client Synchronization. CoRR abs/2202.01268 (2022) - [i153]Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander V. Gasnikov:
Optimal Algorithms for Decentralized Stochastic Variational Inequalities. CoRR abs/2202.02771 (2022) - [i152]Konstantin Burlachenko, Samuel Horváth, Peter Richtárik:
FL_PyTorch: optimization research simulator for federated learning. CoRR abs/2202.03099 (2022) - [i151]Konstantin Mishchenko, Grigory Malinovsky, Sebastian U. Stich, Peter Richtárik:
ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! CoRR abs/2202.09357 (2022) - [i150]Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik, Michael G. Rabbat:
FedShuffle: Recipes for Better Use of Local Work in Federated Learning. CoRR abs/2204.13169 (2022) - [i149]