Nikita Kotelevskii

According to our database, Nikita Kotelevskii authored at least 8 papers between 2020 and 2024.

Collaborative distances:

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

2024

Predictive Uncertainty Quantification via Risk Decompositions for Strictly Proper Scoring Rules.

Nikita Kotelevskii, Maxim Panov

CoRR, 2024

Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks.

Nikita Kotelevskii, Samuel Horváth, Karthik Nandakumar, Martin Takác, Maxim Panov

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

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

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2022

NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks.

Nikita Kotelevskii, Aleksandr Artemenkov, Kirill Fedyanin, Fedor Noskov, Alexander Fishkov, Aleksandr Petiushko, Maxim Panov

CoRR, 2022

FedPop: A Bayesian Approach for Personalised Federated Learning.

Nikita Kotelevskii, Maxime Vono, Alain Durmus, Eric Moulines

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Nonparametric Uncertainty Quantification for Single Deterministic Neural Network.

Nikita Kotelevskii, Aleksandr Artemenkov, Kirill Fedyanin, Fedor Noskov, Alexander Fishkov, Artem Shelmanov, Artem Vazhentsev, Aleksandr Petiushko, Maxim Panov

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Monte Carlo Variational Auto-Encoders.

Achille Thin, Nikita Kotelevskii, Arnaud Doucet, Alain Durmus, Eric Moulines, Maxim Panov

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

2020

MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference.

Achille Thin, Nikita Kotelevskii, Jean-Stanislas Denain, Léo Grinsztajn, Alain Durmus, Maxim Panov, Eric Moulines

CoRR, 2020