Samuel Horvath
Samuel Horvath
Other namesSamuel Horváth
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Verified email at - Homepage
Cited by
Cited by
A field guide to federated optimization
J Wang, Z Charles, Z Xu, G Joshi, HB McMahan, M Al-Shedivat, G Andrew, ...
arXiv preprint arXiv:2107.06917, 2021
FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
S Horvath, S Laskaridis, M Almeida, I Leontiadis, SI Venieris, ND Lane
35th Conference on Neural Information Processing Systems (NeurIPS 2021), 2021
Stochastic Distributed Learning with Gradient Quantization and Variance Reduction
S Horvath, D Kovalev, K Mishchenko, SU Stich, P Richtarik
Optimization Methods and Software, DOI: 10.1080/10556788.2022.2117355, 2022
Lower bounds and optimal algorithms for personalized federated learning
F Hanzely, S Hanzely, S Horváth, P Richtárik
34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020
Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop
D Kovalev, S Horváth, P Richtárik
ALT 2020 - Proceedings of the 31st International Conference on Algorithmic …, 2019
Natural compression for distributed deep learning
S Horváth, CY Ho, L Horvath, AN Sahu, M Canini, P Richtárik
3rd Annual Conference on Mathematical and Scientific Machine Learning (MSML …, 2022
On Biased Compression for Distributed Learning
A Beznosikov, S Horváth, P Richtárik, M Safaryan
Journal of Machine Learning Research 24 (2023), 1--50, 2023
Optimal Client Sampling for Federated Learning
W Chen, S Horvath, P Richtarik
Published in Transactions on Machine Learning Research (TMLR), 2022
A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning
S Horváth, P Richtárik
ICLR 2021 - International Conference on Learning Representations, 2020
Nonconvex variance reduced optimization with arbitrary sampling
S Horváth, P Richtárik
ICML 2019 - Proceedings of the 36th International Conference on Machine Learning, 2018
Variance reduction is an antidote to byzantines: Better rates, weaker assumptions and communication compression as a cherry on the top
E Gorbunov, S Horváth, P Richtárik, G Gidel
ICLR 2023, 2022
Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization
S Horváth, L Lei, P Richtárik, MI Jordan
SIAM Journal on Mathematics of Data Science (SIMODS), 2022
High-probability bounds for stochastic optimization and variational inequalities: the case of unbounded variance
A Sadiev, M Danilova, E Gorbunov, S Horváth, G Gidel, P Dvurechensky, ...
ICML 2023, 2023
Convergence of proximal point and extragradient-based methods beyond monotonicity: the case of negative comonotonicity
E Gorbunov, A Taylor, S Horváth, G Gidel
International Conference on Machine Learning, 11614-11641, 2023
Fedshuffle: Recipes for better use of local work in federated learning
S Horváth, M Sanjabi, L Xiao, P Richtárik, M Rabbat
Published in Transactions on Machine Learning Research (TMLR), 2022
Fl_pytorch: optimization research simulator for federated learning
K Burlachenko, S Horváth, P Richtárik
Proceedings of the 2nd ACM International Workshop on Distributed Machine …, 2021
Hyperparameter transfer learning with adaptive complexity
S Horváth, A Klein, P Richtárik, C Archambeau
International conference on artificial intelligence and statistics, 1378-1386, 2021
FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning
E Gasanov, A Khaled, S Horváth, P Richtárik
AISTATS 2022, International Conference on Artificial Intelligence and Statistics, 2021
Artificial intelligence-driven design of fuel mixtures
N Kuzhagaliyeva, S Horváth, J Williams, A Nicolle, SM Sarathy
Communications Chemistry 5 (1), 111, 2022
Long-term outcome in patients with takotsubo syndrome: A single center study from Vienna
E Pogran, A Abd El-Razek, L Gargiulo, V Weihs, C Kaufmann, S Horváth, ...
Wiener klinische Wochenschrift 134 (7), 261-268, 2022
The system can't perform the operation now. Try again later.
Articles 1–20