Nikita Puchkin

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 14

Top Topics

Stochastic Optimization Problems

Pool Based Active Learning

Top Venues

IEEE Trans. Inf. Theory

Publications

Nikita Puchkin, Eduard Gorbunov, Nikolay Kutuzov, Alexander V. Gasnikov
Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems. AISTATS (2024)
Nikita Puchkin, Maxim V. Rakhuba
Dimension-free Structured Covariance Estimation. COLT (2024)
Nikita Puchkin, Valeriia Shcherbakova
A Contrastive Approach to Online Change Point Detection. AISTATS (2023)
Nikita Puchkin, Nikita Zhivotovskiy
Exploring Local Norms in Exp-concave Statistical Learning. COLT (2023)
Nikita Puchkin, Nikita Zhivotovskiy
Exploring Local Norms in Exp-concave Statistical Learning. CoRR (2023)
Nikita Puchkin, Eduard Gorbunov, Nikolay Kutuzov, Alexander V. Gasnikov
Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems. CoRR (2023)
Denis Belomestny, Alexey Naumov, Nikita Puchkin, Sergey Samsonov
Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations. Neural Networks 161 (2023)
Denis Belomestny, Alexey Naumov, Nikita Puchkin, Sergey Samsonov
Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations. CoRR (2022)
Nikita Puchkin, Valeriia Shcherbakova
A Contrastive Approach to Online Change Point Detection. CoRR (2022)
Nikita Puchkin, Nikita Zhivotovskiy
Exponential Savings in Agnostic Active Learning Through Abstention. IEEE Trans. Inf. Theory 68 (7) (2022)
Nikita Puchkin, Vladimir G. Spokoiny
Structure-adaptive Manifold Estimation. J. Mach. Learn. Res. 23 (2022)
Nikita Puchkin, Nikita Zhivotovskiy
Exponential savings in agnostic active learning through abstention. COLT (2021)
Nikita Puchkin, Nikita Zhivotovskiy
Exponential Savings in Agnostic Active Learning through Abstention. CoRR (2021)
Nikita Puchkin, Vladimir G. Spokoiny
Pointwise adaptation via stagewise aggregation of local estimates for multiclass classification. CoRR (2018)