Saveliy Chezhegov

According to our database, Saveliy Chezhegov authored at least 9 papers between 2022 and 2025.

Collaborative distances:

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

2025

Aligning Distributionally Robust Optimization with Practical Deep Learning Needs.

Dmitrii Feoktistov, Igor Ignashin, Andrey Veprikov, Nikita Borovko, Alexander Bogdanov, Savelii Chezhegov, Aleksandr Beznosikov

CoRR, August, 2025

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level.

Saleh Vatan Khah, Savelii Chezhegov, Shahrokh Farahmand, Samuel Horváth, Eduard Gorbunov

CoRR, July, 2025

Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation.

Dmitry Bylinkin, Mikhail Aleksandrov, Saveliy Chezhegov, Aleksandr Beznosikov

CoRR, July, 2025

Convergence of Clipped-SGD for Convex (L₀,L₁)-Smooth Optimization with Heavy-Tailed Noise.

Saveliy Chezhegov, Aleksandr Beznosikov, Samuel Horváth, Eduard Gorbunov

CoRR, May, 2025

Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling.

Daniil Medyakov, Gleb Molodtsov, Saveliy Chezhegov, Alexey Rebrikov, Aleksandr Beznosikov

CoRR, February, 2025

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed.

Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander V. Gasnikov, Samuel Horváth, Martin Takác, Eduard Gorbunov

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Gradient Clipping Improves AdaGrad when the Noise Is Heavy-Tailed.

Saveliy Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander V. Gasnikov, Samuel Horváth, Martin Takác, Eduard Gorbunov

CoRR, 2024

Local Methods with Adaptivity via Scaling.

Saveliy Chezhegov, Sergey Skorik, Nikolas Khachaturov, Danil Shalagin, Aram Avetisyan, Aleksandr Beznosikov, Martin Takác, Yaroslav Kholodov, Alexander V. Gasnikov

CoRR, 2024

2022

Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes.

Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov, Darina Dvinskikh, Saveliy Chezhegov, Rachael Tappenden, Martin Takác, Alexander V. Gasnikov

EURO J. Comput. Optim., 2022