Sarit Khirirat

According to our database, Sarit Khirirat authored at least 17 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Error Feedback under (L₀,L₁)-Smoothness: Normalization and Momentum.

Sarit Khirirat, Abdurakhmon Sadiev, Artem Riabinin, Eduard Gorbunov, Peter Richtárik

CoRR, 2024

On the Convergence of Federated Learning Algorithms without Data Similarity.

Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon

CoRR, 2024

Distributed Momentum Methods Under Biased Gradient Estimations.

Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon

CoRR, 2024

Compressed Federated Reinforcement Learning with a Generative Model.

Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2024

2023

Improved Step-Size Schedules for Proximal Noisy Gradient Methods.

Sarit Khirirat, Xiaoyu Wang, Sindri Magnússon, Mikael Johansson

IEEE Trans. Signal Process., 2023

Clip21: Error Feedback for Gradient Clipping.

Sarit Khirirat, Eduard Gorbunov, Samuel Horváth, Rustem Islamov, Fakhri Karray, Peter Richtárik

CoRR, 2023

Improving Performance of Private Federated Models in Medical Image Analysis.

Xiangjian Hou, Sarit Khirirat, Mohammad Yaqub, Samuel Horváth

CoRR, 2023

2022

First-Order Algorithms for Communication Efficient Distributed Learning.

Sarit Khirirat

PhD thesis, 2022

Eco-Fedsplit: Federated Learning with Error-Compensated Compression.

Sarit Khirirat, Sindri Magnússon, Mikael Johansson

Proceedings of the IEEE International Conference on Acoustics, 2022

Zeroth-Order Randomized Subspace Newton Methods.

Erik Berglund, Sarit Khirirat, Xiaoyu Wang

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Compressed Gradient Methods With Hessian-Aided Error Compensation.

Sarit Khirirat, Sindri Magnússon, Mikael Johansson

IEEE Trans. Signal Process., 2021

Improved Step-Size Schedules for Noisy Gradient Methods.

Sarit Khirirat, Xiaoyu Wang, Sindri Magnússon, Mikael Johansson

Proceedings of the IEEE International Conference on Acoustics, 2021

A Flexible Framework for Communication-Efficient Machine Learning.

Sarit Khirirat, Sindri Magnússon, Arda Aytekin, Mikael Johansson

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2019

Convergence Bounds for Compressed Gradient Methods with Memory Based Error Compensation.

Sarit Khirirat, Sindri Magnússon, Mikael Johansson

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

The Convergence of Sparsified Gradient Methods.

Dan Alistarh, Torsten Hoefler, Mikael Johansson, Nikola Konstantinov, Sarit Khirirat, Cédric Renggli

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Gradient compression for communication-limited convex optimization.

Sarit Khirirat, Mikael Johansson, Dan Alistarh

Proceedings of the 57th IEEE Conference on Decision and Control, 2018

2017

Mini-batch gradient descent: Faster convergence under data sparsity.

Sarit Khirirat, Hamid Reza Feyzmahdavian, Mikael Johansson

Proceedings of the 56th IEEE Annual Conference on Decision and Control, 2017