Samuel Horváth

110 papers A* 21A 6B 1Journal 73Unranked 8

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC. CoRR Abdulla Jasem Almansoori, Maria Ivanova, Andrey Veprikov, Aleksandr Beznosikov, Samuel Horváth, Martin Takác
2026	J	`jnl`	Byzantine-Robust Optimization under (L CoRR Arman Bolatov, Samuel Horváth, Martin Takác, Eduard Gorbunov
2026	J	`jnl`	FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment. CoRR Riccardo Zaccone, Stefanos Laskaridis, Marco Ciccone, Samuel Horváth
2026	J	`jnl`	Learning in the Null Space: Small Singular Values for Continual Learning. CoRR Cuong Anh Pham, Praneeth Vepakomma, Samuel Horváth
2025	A*	`conf`	Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks. ICML Nurbek Tastan, Samuel Horváth, Karthik Nandakumar
2025	J	`jnl`	Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks. CoRR Nurbek Tastan, Samuel Horváth, Karthik Nandakumar
2025	J	`jnl`	CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning. CoRR Nurbek Tastan, Samuel Horváth, Karthik Nandakumar
2025	J	`jnl`	CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning. Trans. Mach. Learn. Res. Nurbek Tastan, Samuel Horváth, Karthik Nandakumar
2025	A*	`conf`	Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed. ICML Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander V. Gasnikov, Samuel Horváth, Martin Takác, Eduard Gorbunov
2025	—	`conf`	Collaborative and Efficient Personalization with Mixtures of Adaptors. CPAL Abdulla Jasem Almansoori, Samuel Horváth, Martin Takác
2025	J	`jnl`	Convergence of Clipped-SGD for Convex (L CoRR Saveliy Chezhegov, Aleksandr Beznosikov, Samuel Horváth, Eduard Gorbunov
2025	J	`jnl`	DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models. CoRR Alex Iacob, Lorenzo Sani, Mher Safaryan, Paris Giampouras, Samuel Horváth, Andrej Jovanovic, Meghdad Kurmanji, Preslav Aleksandrov, William F. Shen, Xinchi Qiu, Nicholas D. Lane
2025	A	`conf`	DPFL: Decentralized Personalized Federated Learning. AISTATS Salma Kharrat, Marco Canini, Samuel Horváth
2025	J	`jnl`	Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level. CoRR Saleh Vatan Khah, Savelii Chezhegov, Shahrokh Farahmand, Samuel Horváth, Eduard Gorbunov
2025	J	`jnl`	Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy. CoRR Rustem Islamov, Samuel Horváth, Aurélien Lucchi, Peter Richtárik, Eduard Gorbunov
2025	A*	`conf`	FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training. ICML Philip Zmushko, Aleksandr Beznosikov, Martin Takác, Samuel Horváth
2025	J	`jnl`	Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update. CoRR Abdulla Jasem Almansoori, Maria Ivanova, Andrey Veprikov, Aleksandr Beznosikov, Samuel Horváth, Martin Takác
2025	—	`conf`	FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning. CPAL Nurbek Tastan, Samuel Horváth, Martin Takác, Karthik Nandakumar
2025	J	`jnl`	Fishing For Cheap And Efficient Pruners At Initialization. CoRR Ivo Gollini Navarrete, Nicolas Mauricio Cuadrado, Jose Renato Restom, Martin Takác, Samuel Horváth
2025	—	`conf`	Global-QSGD: Allreduce-Compatible Quantization for Distributed Learning with Theoretical Guarantees. EuroMLSys Jihao Xin, Marco Canini, Peter Richtárik, Samuel Horváth
2025	J	`jnl`	LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning. CoRR Nurbek Tastan, Stefanos Laskaridis, Martin Takác, Karthik Nandakumar, Samuel Horváth
2025	J	`jnl`	MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates. CoRR Alex Iacob, Andrej Jovanovic, Mher Safaryan, Meghdad Kurmanji, Lorenzo Sani, Samuel Horváth, William F. Shen, Xinchi Qiu, Nicholas D. Lane
2025	A*	`conf`	Methods for Convex (L0, L1)-Smooth Optimization: Clipping, Acceleration, and Adaptivity. ICLR Eduard Gorbunov, Nazarii Tupitsa, Sayantan Choudhury, Alen Aliev, Peter Richtárik, Samuel Horváth, Martin Takác
2025	A*	`conf`	Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization. ICLR Yury Demidovich, Petr Ostroukhov, Grigory Malinovsky, Samuel Horváth, Martin Takác, Peter Richtárik, Eduard Gorbunov
2025	J	`jnl`	Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity. Trans. Mach. Learn. Res. Konstantin Mishchenko, Rustem Islamov, Eduard Gorbunov, Samuel Horváth
2025	J	`jnl`	Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods. CoRR Andrey Veprikov, Arman Bolatov, Samuel Horváth, Aleksandr Beznosikov, Martin Takác, Slavomír Hanzely
2025	A	`conf`	Quantize Once, Train Fast: Allreduce-Compatible Compression with Provable Guarantees. ECAI Jihao Xin, Marco Canini, Peter Richtárik, Samuel Horváth
2025	A	`conf`	Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis. AISTATS Ruichen Luo, Sebastian U. Stich, Samuel Horváth, Martin Takác
2025	J	`jnl`	Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis. CoRR Ruichen Luo, Sebastian U. Stich, Samuel Horváth, Martin Takác
2025	J	`jnl`	Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees. CoRR Artem Agafonov, Vladislav Ryspayev, Samuel Horváth, Alexander V. Gasnikov, Martin Takác, Slavomír Hanzely
2025	—	`conf`	Towards a Unified Framework for Split Learning. EuroMLSys Boris Radovic, Marco Canini, Samuel Horváth, Veljko Pejovic, Praneeth Vepakomma
2025	—	`conf`	Vanishing Feature: Diagnosing Model Merging and Beyond. CPAL Xingyu Qu, Samuel Horváth
2025	J	`jnl`	Who to Trust? Aggregating Client Knowledge in Logit-Based Federated Learning. CoRR Viktor Kovalchuk, Nikita Kotelevskii, Maxim Panov, Samuel Horváth, Martin Takác
2024	A*	`conf`	Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences. NeurIPS Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov
2024	J	`jnl`	Collaborative and Efficient Personalization with Mixtures of Adaptors. CoRR Abdulla Jasem Almansoori, Samuel Horváth, Martin Takác
2024	J	`jnl`	Decentralized Personalized Federated Learning. CoRR Salma Kharrat, Marco Canini, Samuel Horváth
2024	A*	`conf`	Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks. IJCAI Nikita Kotelevskii, Samuel Horváth, Karthik Nandakumar, Martin Takác, Maxim Panov
2024	A	`conf`	Efficient Conformal Prediction under Data Heterogeneity. AISTATS Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov
2024	J	`jnl`	Enhancing Policy Gradient with the Polyak Step-Size Adaption. CoRR Yunxiang Li, Rui Yuan, Chen Fan, Mark Schmidt, Samuel Horváth, Robert M. Gower, Martin Takác
2024	J	`jnl`	FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training. CoRR Philip Zmushko, Aleksandr Beznosikov, Martin Takác, Samuel Horváth
2024	J	`jnl`	FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning. CoRR Nurbek Tastan, Samuel Horváth, Martin Takác, Karthik Nandakumar
2024	J	`jnl`	Federated Learning Can Find Friends That Are Beneficial. CoRR Nazarii Tupitsa, Samuel Horváth, Martin Takác, Eduard Gorbunov
2024	J	`jnl`	Flashback: Understanding and Mitigating Forgetting in Federated Learning. CoRR Mohammed Aljahdali, Ahmed M. Abdelmoniem, Marco Canini, Samuel Horváth
2024	J	`jnl`	Generalized Policy Learning for Smart Grids: FL TRPO Approach. CoRR Yunxiang Li, Nicolas Mauricio Cuadrado, Samuel Horváth, Martin Takác
2024	J	`jnl`	Generalizing in Net-Zero Microgrids: A Study with Federated PPO and TRPO. CoRR Nicolas Mauricio Cuadrado, Samuel Horváth, Martin Takác
2024	J	`jnl`	Gradient Clipping Improves AdaGrad when the Noise Is Heavy-Tailed. CoRR Saveliy Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander V. Gasnikov, Samuel Horváth, Martin Takác, Eduard Gorbunov
2024	A*	`conf`	High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise. ICML Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
2024	J	`jnl`	Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning. CoRR Kaustubh Ponkshe, Raghav Singhal, Eduard Gorbunov, Alexey Tumanov, Samuel Horváth, Praneeth Vepakomma
2024	—	`conf`	Low-Resource Machine Translation through the Lens of Personalized Federated Learning. EMNLP (Findings) Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, Samuel Horváth, Eduard Gorbunov, Irina Nikishina
2024	J	`jnl`	Low-Resource Machine Translation through the Lens of Personalized Federated Learning. CoRR Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, Samuel Horváth, Eduard Gorbunov, Irina Nikishina
2024	A*	`conf`	Maestro: Uncovering Low-Rank Structures via Trainable Decomposition. ICML Samuel Horváth, Stefanos Laskaridis, Shashank Rajput, Hongyi Wang
2024	J	`jnl`	Methods for Convex (L CoRR Eduard Gorbunov, Nazarii Tupitsa, Sayantan Choudhury, Alen Aliev, Peter Richtárik, Samuel Horváth, Martin Takác
2024	J	`jnl`	Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization. CoRR Yury Demidovich, Petr Ostroukhov, Grigory Malinovsky, Samuel Horváth, Martin Takác, Peter Richtárik, Eduard Gorbunov
2024	J	`jnl`	PaDPaF: Partial Disentanglement with Partially-Federated GANs. Trans. Mach. Learn. Res. Abdulla Jasem Almansoori, Samuel Horváth, Martin Takác
2024	A*	`conf`	Redefining Contributions: Shapley-Driven Federated Learning. IJCAI Nurbek Tastan, Samar Fares, Toluwani Aremu, Samuel Horváth, Karthik Nandakumar
2024	J	`jnl`	Redefining Contributions: Shapley-Driven Federated Learning. CoRR Nurbek Tastan, Samar Fares, Toluwani Aremu, Samuel Horváth, Karthik Nandakumar
2024	A*	`conf`	Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad. NeurIPS Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horváth, Martin Takác, Eduard Gorbunov
2024	J	`jnl`	Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad. CoRR Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horváth, Martin Takác, Eduard Gorbunov
2023	A*	`conf`	Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance. NeurIPS Nikita Kornilov, Ohad Shamir, Aleksandr V. Lobanov, Darina Dvinskikh, Alexander V. Gasnikov, Innokentiy Shibaev, Eduard Gorbunov, Samuel Horváth
2023	J	`jnl`	Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences. CoRR Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov
2023	A*	`conf`	Byzantine-Tolerant Methods for Distributed Variational Inequalities. NeurIPS Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu, Martin Takác, Karthik Nandakumar, Samuel Horváth, Eduard Gorbunov
2023	J	`jnl`	Byzantine-Tolerant Methods for Distributed Variational Inequalities. CoRR Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu, Martin Takác, Karthik Nandakumar, Samuel Horváth, Eduard Gorbunov
2023	J	`jnl`	Clip21: Error Feedback for Gradient Clipping. CoRR Sarit Khirirat, Eduard Gorbunov, Samuel Horváth, Rustem Islamov, Fakhri Karray, Peter Richtárik
2023	A*	`conf`	Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity. ICML Eduard Gorbunov, Adrien B. Taylor, Samuel Horváth, Gauthier Gidel
2023	J	`jnl`	Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks. CoRR Nikita Kotelevskii, Samuel Horváth, Karthik Nandakumar, Martin Takác, Maxim Panov
2023	J	`jnl`	Efficient Conformal Prediction under Data Heterogeneity. CoRR Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov
2023	J	`jnl`	Federated Learning with Regularized Client Participation. CoRR Grigory Malinovsky, Samuel Horváth, Konstantin Burlachenko, Peter Richtárik
2023	J	`jnl`	Global-QSGD: Practical Floatless Quantization for Distributed Learning with Theoretical Guarantees. CoRR Jihao Xin, Marco Canini, Peter Richtárik, Samuel Horváth
2023	A*	`conf`	Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition. NeurIPS Sara Pieri, Jose Renato Restom, Samuel Horváth, Hisham Cholakkal
2023	J	`jnl`	Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition. CoRR Sara Pieri, Jose Renato Restom, Samuel Horváth, Hisham Cholakkal
2023	A*	`conf`	High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance. ICML Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
2023	J	`jnl`	High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance. CoRR Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
2023	J	`jnl`	High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise. CoRR Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
2023	J	`jnl`	Improving Performance of Private Federated Models in Medical Image Analysis. CoRR Xiangjian Hou, Sarit Khirirat, Mohammad Yaqub, Samuel Horváth
2023	J	`jnl`	Maestro: Uncovering Low-Rank Structures via Trainable Decomposition. CoRR Samuel Horváth, Stefanos Laskaridis, Shashank Rajput, Hongyi Wang
2023	J	`jnl`	On Biased Compression for Distributed Learning. J. Mach. Learn. Res. Aleksandr Beznosikov, Samuel Horváth, Peter Richtárik, Mher Safaryan
2023	J	`jnl`	Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity. CoRR Konstantin Mishchenko, Rustem Islamov, Eduard Gorbunov, Samuel Horváth
2023	J	`jnl`	Stochastic distributed learning with gradient quantization and double-variance reduction. Optim. Methods Softw. Samuel Horváth, Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik, Sebastian U. Stich
2023	A*	`conf`	Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top. ICLR Eduard Gorbunov, Samuel Horváth, Peter Richtárik, Gauthier Gidel
2022	J	`jnl`	Adaptive Learning Rates for Faster Stochastic Gradient Methods. CoRR Samuel Horváth, Konstantin Mishchenko, Peter Richtárik
2022	J	`jnl`	Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization. SIAM J. Math. Data Sci. Samuel Horváth, Lihua Lei, Peter Richtárik, Michael I. Jordan
2022	J	`jnl`	Better Methods and Theory for Federated Learning: Compression, Client Selection and Heterogeneity. CoRR Samuel Horváth
2022	—	`—`	Better Methods and Theory for Federated Learning: Compression, Client Selection and Heterogeneity. Samuel Horváth
2022	A	`conf`	FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning. AISTATS Elnur Gasanov, Ahmed Khaled, Samuel Horváth, Peter Richtárik
2022	J	`jnl`	FL_PyTorch: optimization research simulator for federated learning. CoRR Konstantin Burlachenko, Samuel Horváth, Peter Richtárik
2022	J	`jnl`	FedShuffle: Recipes for Better Use of Local Work in Federated Learning. CoRR Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik, Michael G. Rabbat
2022	J	`jnl`	FedShuffle: Recipes for Better Use of Local Work in Federated Learning. Trans. Mach. Learn. Res. Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik, Michael G. Rabbat
2022	J	`jnl`	Granger Causality using Neural Networks. CoRR Samuel Horváth, Malik Shahid Sultan, Hernando Ombao
2022	—	`conf`	Natural Compression for Distributed Deep Learning. MSML Samuel Horváth, Chen-Yu Ho, Ludovit Horvath, Atal Narayan Sahu, Marco Canini, Peter Richtárik
2022	J	`jnl`	Optimal Client Sampling for Federated Learning. Trans. Mach. Learn. Res. Wenlin Chen, Samuel Horváth, Peter Richtárik
2022	J	`jnl`	Partial Disentanglement with Partially-Federated GANs (PaDPaF). CoRR Abdulla Jasem Almansoori, Samuel Horváth, Martin Takác
2022	J	`jnl`	Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top. CoRR Eduard Gorbunov, Samuel Horváth, Peter Richtárik, Gauthier Gidel
2021	A*	`conf`	A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning. ICLR Samuel Horváth, Peter Richtárik
2021	J	`jnl`	A Field Guide to Federated Optimization. CoRR Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, Blaise Agüera y Arcas, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, Suhas N. Diggavi, Hubert Eichner, Advait Gadhikar, Zachary Garrett, Antonious M. Girgis, Filip Hanzely, Andrew Hard, Chaoyang He, Samuel Horváth, Zhouyuan Huo, Alex Ingerman, Martin Jaggi, Tara Javidi, Peter Kairouz, Satyen Kale, Sai Praneeth Karimireddy, Jakub Konecný, Sanmi Koyejo, Tian Li, Luyang Liu, Mehryar Mohri, Hang Qi, Sashank J. Reddi, Peter Richtárik, Karan Singhal, Virginia Smith, Mahdi Soltanolkotabi, Weikang Song, Ananda Theertha Suresh, Sebastian U. Stich, Ameet Talwalkar, Hongyi Wang, Blake E. Woodworth, Shanshan Wu, Felix X. Yu, Honglin Yuan, Manzil Zaheer, Mi Zhang, Tong Zhang, Chunxiang Zheng, Chen Zhu, Wennan Zhu
2021	J	`jnl`	FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning. CoRR Elnur Gasanov, Ahmed Khaled, Samuel Horváth, Peter Richtárik
2021	—	`conf`	FL_PyTorch: optimization research simulator for federated learning. DistributedML@CoNEXT Konstantin Burlachenko, Samuel Horváth, Peter Richtárik
2021	A*	`conf`	FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout. NeurIPS Samuel Horváth, Stefanos Laskaridis, Mário Almeida, Ilias Leontiadis, Stylianos I. Venieris, Nicholas D. Lane
2021	J	`jnl`	FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout. CoRR Samuel Horváth, Stefanos Laskaridis, Mário Almeida, Ilias Leontiadis, Stylianos I. Venieris, Nicholas D. Lane
2021	A	`conf`	Hyperparameter Transfer Learning with Adaptive Complexity. AISTATS Samuel Horváth, Aaron Klein, Peter Richtárik, Cédric Archambeau
2021	J	`jnl`	Hyperparameter Transfer Learning with Adaptive Complexity. CoRR Samuel Horváth, Aaron Klein, Peter Richtárik, Cédric Archambeau
2020	J	`jnl`	A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning. CoRR Samuel Horváth, Peter Richtárik
2020	J	`jnl`	Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization. CoRR Samuel Horváth, Lihua Lei, Peter Richtárik, Michael I. Jordan
2020	B	`conf`	Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop. ALT Dmitry Kovalev, Samuel Horváth, Peter Richtárik
2020	A*	`conf`	Lower Bounds and Optimal Algorithms for Personalized Federated Learning. NeurIPS Filip Hanzely, Slavomír Hanzely, Samuel Horváth, Peter Richtárik
2020	J	`jnl`	Lower Bounds and Optimal Algorithms for Personalized Federated Learning. CoRR Filip Hanzely, Slavomír Hanzely, Samuel Horváth, Peter Richtárik
2020	J	`jnl`	On Biased Compression for Distributed Learning. CoRR Aleksandr Beznosikov, Samuel Horváth, Peter Richtárik, Mher Safaryan
2020	J	`jnl`	Optimal Client Sampling for Federated Learning. CoRR Wenlin Chen, Samuel Horváth, Peter Richtárik
2019	J	`jnl`	Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop. CoRR Dmitry Kovalev, Samuel Horváth, Peter Richtárik
2019	J	`jnl`	Natural Compression for Distributed Deep Learning. CoRR Samuel Horváth, Chen-Yu Ho, Ludovit Horvath, Atal Narayan Sahu, Marco Canini, Peter Richtárik
2019	A*	`conf`	Nonconvex Variance Reduced Optimization with Arbitrary Sampling. ICML Samuel Horváth, Peter Richtárik