Samuel Horváth

Most-cited papers

1. Lower Bounds and Optimal Algorithms for Personalized Federated Learning

   Filip Hanzely, S. Hanzely, Samuel Horváth, Peter Richtárik

   2020Neural Information Processing Systems217 citations

   Semantic Scholar

   Save

2. Stochastic Distributed Learning with Gradient Quantization and Variance Reduction

   Samuel Horváth, Dmitry Kovalev, Konstantin Mishchenko, Sebastian U. Stich +1 more

   2019143 citations

   Semantic Scholar

   Save

3. Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top

   Eduard A. Gorbunov, Samuel Horváth, Peter Richtárik, G. Gidel

   2023International Conference on Learning Representations68 citations Open access

   Semantic Scholar

   Save

4. A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning

   Samuel Horváth, Peter Richtárik

   2020International Conference on Learning Representations68 citations

   Semantic Scholar

   Save

5. Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization

   Samuel Horváth, Li-Hua Lei, Peter Richtárik, Michael I. Jordan

   2020SIAM Journal on Mathematics of Data Science36 citations Open access

   Semantic Scholar

   Save

6. Hyperparameter Transfer Learning with Adaptive Complexity

   Samuel Horváth, Aaron Klein, Peter Richtárik, C. Archambeau

   2021International Conference on Artificial Intelligence and Statistics26 citations

   Semantic Scholar

   Save

7. Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity

   Eduard A. Gorbunov, Adrien B. Taylor, Samuel Horváth, G. Gidel

   2022International Conference on Machine Learning24 citations

   Semantic Scholar

   Save

8. FedShuffle: Recipes for Better Use of Local Work in Federated Learning

   Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik +1 more

   2022Trans. Mach. Learn. Res.23 citations Open access

   Semantic Scholar

   Save

9. FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning

   Эльнур Лятиф Гасанов, Ahmed Khaled, Samuel Horváth, Peter Richtárik

   2021International Conference on Artificial Intelligence and Statistics18 citations

   Semantic Scholar

   Save

10. Adaptive Learning Rates for Faster Stochastic Gradient Methods

    Samuel Horváth, Konstantin Mishchenko, Peter Richtárik

    2022arXiv.org13 citations Open access

    Semantic Scholar

    Save

11. Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences

    G. Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov

    2023arXiv.org11 citations

    Semantic Scholar

    Save

12. Flashback: Understanding and Mitigating Forgetting in Federated Learning

    Mohammed M. Aljahdali, A. Abdelmoniem, Marco Canini, Samuel Horváth

    20242025 3rd International Conference on Federated Learning Technologies and Applications (FLTA)6 citations Open access

    Semantic Scholar

    Save

13. Federated Learning Can Find Friends That Are Beneficial

    Nazarii Tupitsa, Samuel Horváth, Martin Takác, Eduard Gorbunov

    2024arXiv.org3 citations

    Semantic Scholar

    Save

14. Better Methods and Theory for Federated Learning: Compression, Client Selection and Heterogeneity

    Samuel Horváth

    2022arXiv.org2 citations Open access

    Semantic Scholar

    Save

15. Modulated learning for private and distributed regression with just a single sample per client device

    Praneeth Vepakomma, Amirhossein Reisizadeh, Samuel Horváth, M. Dahleh

    2026arXiv.org0 citations

    Semantic Scholar

    Save