Konstantin Burlachenko

According to our database, Konstantin Burlachenko authored at least 12 papers between 2021 and 2024.

Collaborative distances:

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

2024

Faster Rates for Compressed Federated Learning with Client-Variance Reduction.

Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtárik

SIAM J. Math. Data Sci., March, 2024

Unlocking FedNL: Self-Contained Compute-Optimized Implementation.

Konstantin Burlachenko, Peter Richtárik

CoRR, 2024

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression.

Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtárik

CoRR, 2024

Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants.

Peter Richtárik, Elnur Gasanov, Konstantin Burlachenko

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling.

Alexander Tyurin, Lukang Sun, Konstantin Burlachenko, Peter Richtárik

Trans. Mach. Learn. Res., 2023

Personalized Federated Learning with Communication Compression.

El Houcine Bergou, Konstantin Burlachenko, Aritra Dutta, Peter Richtárik

Trans. Mach. Learn. Res., 2023

Error Feedback Shines when Features are Rare.

Peter Richtárik, Elnur Gasanov, Konstantin Burlachenko

CoRR, 2023

Federated Learning with Regularized Client Participation.

Grigory Malinovsky, Samuel Horváth, Konstantin Burlachenko, Peter Richtárik

CoRR, 2023

Federated Learning is Better with Non-Homomorphic Encryption.

Konstantin Burlachenko, Abdulmajeed Alrowithi, Fahad Ali Albalawi, Peter Richtárik

Proceedings of the 4th International Workshop on Distributed Machine Learning, 2023

2022

Federated Optimization Algorithms with Random Reshuffling and Gradient Compression.

Abdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov, Ahmed Khaled, Konstantin Burlachenko, Peter Richtárik

CoRR, 2022

2021

MARINA: Faster Non-Convex Distributed Learning with Compression.

Eduard Gorbunov, Konstantin Burlachenko, Zhize Li, Peter Richtárik

Proceedings of the 38th International Conference on Machine Learning, 2021

FL_PyTorch: optimization research simulator for federated learning.

Konstantin Burlachenko, Samuel Horváth, Peter Richtárik

Proceedings of the DistributedML '21: Proceedings of the 2nd ACM International Workshop on Distributed Machine Learning, 2021