Publications

Thesis

Khirirat, S. (2022). First-Order Algorithms for Communication Efficient Distributed Learning. 

Preprints 

1. Shulgin, E., Khirirat, S., & Richtárik, P. (2025).
   Smoothed Normalization for Efficient Distributed Private Optimization.
   arXiv preprint arXiv:2502.13482.

2. Khirirat, S., Gorbunov, E., Horváth, S., Islamov, R., Karray, F., & Richtárik, P. (2023).
   Clip21: Error feedback for gradient clipping.
   arXiv preprint arXiv:2305.18929.

3. Khirirat, S., Feyzmahdavian, H. R., & Johansson, M. (2018).
   Distributed learning with compressed gradients.
   arXiv preprint arXiv:1806.06573. 

Journal Papers  

1. Beikmohammadi, A., Khirirat, S., & Magnússon, S. (2025).
   Parallel Momentum Methods Under Biased Gradient Estimations.
   IEEE Transactions on Control of Network Systems.

2. Vaishnav, S., Khirirat, S., & Magnússon, S. (2024).
   Communication-Adaptive Gradient Sparsification for Federated Learning with Error Compensation.
   IEEE Internet of Things Journal. (IEEE-IoT 2024) 

3. Beikmohammadi, A., Khirirat, S., & Magnússon, S. (2024).
   On the convergence of federated learning algorithms without data similarity.
   IEEE Transactions on Big Data, 11(2), 659-668.  

4. Khirirat, S., Wang, X., Magnusson, S., & Johansson, M. (2023).
   Improved step-size schedules for proximal noisy gradient methods.
   IEEE Transactions on Signal Processing, 71, 189-201. (IEEE-TSP 2023)  

5. Khirirat, S., Magnusson, S., & Johansson, M. (2020).
   Compressed gradient methods with hessian-aided error compensation.
   IEEE Transactions on Signal Processing, 69, 998-1011. (IEEE-TSP 2020)  

Conference Papers  

1. Khirirat, S., Sadiev, A., Riabinin, A., Gorbunov, E., & Richtárik, P. (2025).
   Error Feedback under (L_0,L_1)-Smoothness.
   In Advances in Neural Information Processing Systems (NeurIPS). (NeurIPS 2025)  

2. Beikmohammadi, A., Khirirat, S., Richtárik, P., & Magnússon, S. (2025).
   Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis.
   In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 41-58).
   Cham: Springer Nature Switzerland. (ECML 2025)  

3. Hou, X., Khirirat, S., Yaqub, M., & Horváth, S. (2024).
   Balancing Privacy and Performance for Private Federated Learning Algorithms.
   In International Conference on Federated Learning Technologies and Applications (FLTA) (pp. 171-178). 

4. Beikmohammadi, A., Khirirat, S., & Magnússon, S. (2024).
   Compressed federated reinforcement learning with a generative model.
   In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 20-37).
   Cham: Springer Nature Switzerland. (ECML 2024)  

5. Berglund, E., Khirirat, S., Wu, X., Magnússon, S., & Johansson, M. (2023).
   Revisiting the Curvature-aided IAG: Improved Theory and Reduced Complexity.
   IFAC-PapersOnLine, 56(2), 5221-5226.

6. Khirirat, S., Magnússon, S., & Johansson, M. (2022).
   Eco-fedsplit: Federated learning with error-compensated compression.
   In 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5952-5956). 

7. Berglund, E., Khirirat, S., & Wang, X. (2022).
   Zeroth-order randomized subspace Newton methods.
   In 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 6002-6006).  

8. Khirirat, S., Magnússon, S., Aytekin, A., & Johansson, M. (2021).
   A flexible framework for communication-efficient machine learning.
   In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 35, No. 9, pp. 8101-8109).  (AAAI 2021)  

9. Khirirat, S., Wang, X., Magnússon, S., & Johansson, M. (2021).
   Improved step-size schedules for noisy gradient methods.
   In 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 3655-3659). 

10. Khirirat, S., Magnússon, S., & Johansson, M. (2019).
    Convergence bounds for compressed gradient methods with memory based error compensation.
    In 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2857-2861). 
    (Best Student Paper Award)

11. Alistarh, D., Hoefler, T., Johansson, M., Konstantinov, N., Khirirat, S., & Renggli, C. (2018).
    The convergence of sparsified gradient methods. In Advances in Neural Information Processing Systems, 31. (NeurIPS 2018)  

12. Khirirat, S., Johansson, M., & Alistarh, D. (2018).
    Gradient compression for communication-limited convex optimization.
    In 2018 IEEE Conference on Decision and Control (CDC) (pp. 166-171). 

13. Khirirat, S., Feyzmahdavian, H. R., & Johansson, M. (2017).
    Mini-batch gradient descent: Faster convergence under data sparsity.
    In 2017 IEEE 56th Annual Conference on Decision and Control (CDC) (pp. 2880-2887).