Maksim Velikanov

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 13

Top Topics

Conjugate Gradient

Technical Report

Generalization Error Bounds

Top Venues

Publications

Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov
Efficient Conformal Prediction under Data Heterogeneity. AISTATS (2024)
Maksim Velikanov, Maxim Panov, Dmitry Yarotsky
Generalization error of spectral algorithms. CoRR (2024)
Maksim Velikanov, Maxim Panov, Dmitry Yarotsky
Generalization error of spectral algorithms. ICLR (2024)
Quentin Malartic, Nilabhra Roy Chowdhury, Ruxandra Cojocaru, Mugariya Farooq, Giulia Campesan, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Ankit Singh, Maksim Velikanov, Basma El Amel Boussaha, Mohammed Al-Yafeai, Hamza Alobeidli, Leen Al Qadi, Mohamed El Amine Seddik, Kirill Fedyanin, Réda Alami, Hakim Hacid
Falcon2-11B Technical Report. CoRR (2024)
Anastasia Antsiferova, Khaled Abud, Aleksandr Gushchin, Sergey Lavrushkin, Ekaterina Shumitskaya, Maksim Velikanov, Dmitriy S. Vatolin
Comparing the robustness of modern no-reference image- and video-quality metrics to adversarial attacks. CoRR (2023)
Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horváth, Martin Takác, Eric Moulines, Maxim Panov
Efficient Conformal Prediction under Data Heterogeneity. CoRR (2023)
Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. ICLR (2023)
Maksim Velikanov, Dmitry Yarotsky
Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions. CoRR (2022)
Maksim Velikanov, Roman Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky
Embedded Ensembles: Infinite Width Limit and Operating Regimes. CoRR (2022)
Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. CoRR (2022)
Maksim Velikanov, Roman V. Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky
Embedded Ensembles: infinite width limit and operating regimes. AISTATS (2022)
Maksim Velikanov, Dmitry Yarotsky
Explicit loss asymptotics in the gradient descent training of neural networks. NeurIPS (2021)
Maksim Velikanov, Dmitry Yarotsky
Universal scaling laws in the gradient descent training of neural networks. CoRR (2021)