Sarit Khirirat

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 16

Top Topics

Error Compensation

Medical Image Analysis

Steepest Ascent

Gradient Method

Top Venues

IEEE Trans. Signal Process.

Publications

Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon
Distributed Momentum Methods Under Biased Gradient Estimations. CoRR (2024)
Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon
On the Convergence of Federated Learning Algorithms without Data Similarity. CoRR (2024)
Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon
Compressed Federated Reinforcement Learning with a Generative Model. CoRR (2024)
Xiangjian Hou, Sarit Khirirat, Mohammad Yaqub, Samuel Horváth
Improving Performance of Private Federated Models in Medical Image Analysis. CoRR (2023)
Sarit Khirirat, Xiaoyu Wang, Sindri Magnússon, Mikael Johansson
Improved Step-Size Schedules for Proximal Noisy Gradient Methods. IEEE Trans. Signal Process. 71 (2023)
Sarit Khirirat, Eduard Gorbunov, Samuel Horváth, Rustem Islamov, Fakhri Karray, Peter Richtárik
Clip21: Error Feedback for Gradient Clipping. CoRR (2023)
Erik Berglund, Sarit Khirirat, Xiaoyu Wang
Zeroth-Order Randomized Subspace Newton Methods. ICASSP (2022)
Sarit Khirirat, Sindri Magnússon, Mikael Johansson
Eco-Fedsplit: Federated Learning with Error-Compensated Compression. ICASSP (2022)
Sarit Khirirat, Xiaoyu Wang, Sindri Magnússon, Mikael Johansson
Improved Step-Size Schedules for Noisy Gradient Methods. ICASSP (2021)
Sarit Khirirat, Sindri Magnússon, Arda Aytekin, Mikael Johansson
A Flexible Framework for Communication-Efficient Machine Learning. AAAI (2021)
Sarit Khirirat, Sindri Magnússon, Mikael Johansson
Compressed Gradient Methods With Hessian-Aided Error Compensation. IEEE Trans. Signal Process. 69 (2021)
Sarit Khirirat, Sindri Magnússon, Mikael Johansson
Convergence Bounds for Compressed Gradient Methods with Memory Based Error Compensation. ICASSP (2019)
Dan Alistarh, Torsten Hoefler, Mikael Johansson, Nikola Konstantinov, Sarit Khirirat, Cédric Renggli
The Convergence of Sparsified Gradient Methods. NeurIPS (2018)
Dan Alistarh, Torsten Hoefler, Mikael Johansson, Sarit Khirirat, Nikola Konstantinov, Cédric Renggli
The Convergence of Sparsified Gradient Methods. CoRR (2018)
Sarit Khirirat, Mikael Johansson, Dan Alistarh
Gradient compression for communication-limited convex optimization. CDC (2018)
Sarit Khirirat, Hamid Reza Feyzmahdavian, Mikael Johansson
Mini-batch gradient descent: Faster convergence under data sparsity. CDC (2017)