Maksim Velikanov

According to our database, Maksim Velikanov authored at least 8 papers between 2021 and 2024.

Collaborative distances:

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

2024

Generalization error of spectral algorithms.

Maksim Velikanov, Maxim Panov, Dmitry Yarotsky

CoRR, 2024

2023

Efficient Conformal Prediction under Data Heterogeneity.

Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov

CoRR, 2023

Comparing the robustness of modern no-reference image- and video-quality metrics to adversarial attacks.

Anastasia Antsiferova, Khaled Abud, Aleksandr Gushchin, Sergey Lavrushkin, Ekaterina Shumitskaya, Maksim Velikanov, Dmitriy S. Vatolin

CoRR, 2023

A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.

Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions.

Maksim Velikanov, Dmitry Yarotsky

CoRR, 2022

Embedded Ensembles: infinite width limit and operating regimes.

Maksim Velikanov, Roman V. Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Universal scaling laws in the gradient descent training of neural networks.

Maksim Velikanov, Dmitry Yarotsky

CoRR, 2021

Explicit loss asymptotics in the gradient descent training of neural networks.

Maksim Velikanov, Dmitry Yarotsky

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021