Nikita Puchkin

According to our database, Nikita Puchkin authored at least 18 papers between 2018 and 2026.

Collaborative distances:

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

2026

Schrödinger bridge problem via empirical risk minimization.

Denis Belomestny, Alexey Naumov, Nikita Puchkin, Denis Suchkov

CoRR, February, 2026

2025

Implicit score matching meets denoising score matching: improved rates of convergence and log-density Hessian estimation.

Konstantin Yakovlev, Anna Markovich, Nikita Puchkin

CoRR, December, 2025

Simultaneous Approximation of the Score Function and Its Derivatives by Deep Neural Networks.

Konstantin Yakovlev, Nikita Puchkin

CoRR, December, 2025

Approximation Capabilities of Feedforward Neural Networks with GELU Activations.

Konstantin Yakovlev, Nikita Puchkin

CoRR, December, 2025

Tight Bounds for Schrödinger Potential Estimation in Unpaired Image-to-Image Translation Problems.

Nikita Puchkin, Denis Suchkov, Alexey Naumov, Denis Belomestny

CoRR, August, 2025

Sample complexity of Schrödinger potential estimation.

Nikita Puchkin, Iurii Pustovalov, Yuri Sapronov, Denis Suchkov, Alexey Naumov, Denis Belomestny

CoRR, June, 2025

Dimension-free bounds in high-dimensional linear regression via error-in-operator approach.

Fedor Noskov, Nikita Puchkin, Vladimir G. Spokoiny

CoRR, February, 2025

Generalization error bound for denoising score matching under relaxed manifold assumption.

Konstantin Yakovlev, Nikita Puchkin

Proceedings of the Thirty Eighth Annual Conference on Learning Theory, 2025

2024

Rates of convergence for density estimation with generative adversarial networks.

Nikita Puchkin, Sergey Samsonov, Denis Belomestny, Eric Moulines, Alexey Naumov

J. Mach. Learn. Res., 2024

Score-based change point detection via tracking the best of infinitely many experts.

Anna Markovich, Nikita Puchkin

CoRR, 2024

Dimension-free Structured Covariance Estimation.

Nikita Puchkin, Maxim V. Rakhuba

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems.

Nikita Puchkin, Eduard Gorbunov, Nikolay Kutuzov, Alexander V. Gasnikov

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

2023

Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations.

Denis Belomestny, Alexey Naumov, Nikita Puchkin, Sergey Samsonov

Neural Networks, April, 2023

Exploring Local Norms in Exp-concave Statistical Learning.

Nikita Puchkin, Nikita Zhivotovskiy

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

A Contrastive Approach to Online Change Point Detection.

Nikita Puchkin, Valeriia Shcherbakova

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Structure-adaptive Manifold Estimation.

Nikita Puchkin, Vladimir G. Spokoiny

J. Mach. Learn. Res., 2022

2021

Exponential savings in agnostic active learning through abstention.

Nikita Puchkin, Nikita Zhivotovskiy

Proceedings of the Conference on Learning Theory, 2021

2018

Pointwise adaptation via stagewise aggregation of local estimates for multiclass classification.

Nikita Puchkin, Vladimir G. Spokoiny

CoRR, 2018