Follow
Sarit Khirirat
Title
Cited by
Cited by
Year
The convergence of sparsified gradient methods
D Alistarh, T Hoefler, M Johansson, N Konstantinov, S Khirirat, C Renggli
Advances in Neural Information Processing Systems 31, 2018
5372018
Mini-batch gradient descent: Faster convergence under data sparsity
S Khirirat, HR Feyzmahdavian, M Johansson
2017 IEEE 56th Annual Conference on Decision and Control (CDC), 2880-2887, 2017
1162017
Distributed learning with compressed gradients
S Khirirat, HR Feyzmahdavian, M Johansson
arXiv preprint arXiv:1806.06573, 2018
882018
Compressed gradient methods with hessian-aided error compensation
S Khirirat, S Magnússon, M Johansson
IEEE Transactions on Signal Processing 69, 998-1011, 2020
162020
Gradient compression for communication-limited convex optimization
S Khirirat, M Johansson, D Alistarh
2018 IEEE Conference on Decision and Control (CDC), 166-171, 2018
132018
A flexible framework for communication-efficient machine learning
S Khirirat, S Magnússon, A Aytekin, M Johansson
Proceedings of the AAAI Conference on Artificial Intelligence 35 (9), 8101-8109, 2021
112021
Communication efficient sparsification for large scale machine learning
S Khirirat, S Magnússon, A Aytekin, M Johansson
arXiv preprint arXiv:2003.06377, 2020
92020
Improved step-size schedules for proximal noisy gradient methods
S Khirirat, X Wang, S Magnússon, M Johansson
IEEE Transactions on Signal Processing 71, 189-201, 2023
72023
Clip21: Error feedback for gradient clipping
S Khirirat, E Gorbunov, S Horváth, R Islamov, F Karray, P Richtárik
arXiv preprint arXiv:2305.18929, 2023
32023
Eco-Fedsplit: Federated learning with error-compensated compression
S Khirirat, S Magnússon, M Johansson
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
32022
Improved step-size schedules for noisy gradient methods
S Khirirat, X Wang, S Magnússon, M Johansson
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
32021
Compressed Federated Reinforcement Learning with a Generative Model
A Beikmohammadi, S Khirirat, S Magnússon
arXiv preprint arXiv:2404.10635, 2024
22024
Zeroth-order randomized subspace Newton methods
E Berglund, S Khirirat, X Wang
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
22022
A flexible framework for communication-efficient machine learning: from HPC to IoT
S Khirirat, S Magnússon, A Aytekin, M Johansson
arXiv preprint arXiv:2003.06377, 2020
22020
Convergence bounds for compressed gradient methods with memory based error compensation
S Khirirat, S Magnússon, M Johansson
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
22019
Randomized first-order methods for convex optimization
S Khirirat
Master's thesis. KTH Royal Institute of Technoloay, Stockholm, 2016
22016
On the Convergence of Federated Learning Algorithms without Data Similarity
A Beikmohammadi, S Khirirat, S Magnússon
arXiv preprint arXiv:2403.02347, 2024
12024
Distributed Momentum Methods Under Biased Gradient Estimations
A Beikmohammadi, S Khirirat, S Magnússon
arXiv preprint arXiv:2403.00853, 2024
12024
Randomized first-order methods for convex optimization: Improved convergence rate bounds and experimental evaluations
S Khirirat
12016
Improving Performance of Private Federated Models in Medical Image Analysis
X Hou, S Khirirat, M Yaqub, S Horvath
arXiv preprint arXiv:2304.05127, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–20