Alexey Naumov

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 40

Top Topics

Temporal Difference

Variance Reduction

Stochastic Approximation

Top Venues

Publications

Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard
Demonstration-Regularized RL. ICLR (2024)
Sergey Samsonov, Eric Moulines, Qi-Man Shao, Zhuo-Song Zhang, Alexey Naumov
Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning. CoRR (2024)
Daniil Tiapkin, Nikita Morozov, Alexey Naumov, Dmitry P. Vetrov
Generative Flow Networks as Entropy-Regularized RL. AISTATS (2024)
Mikhail Gorbunov, Nikolay Yudin, Vera Soboleva, Aibek Alanov, Alexey Naumov, Maxim Rakhuba
Group and Shuffle: Efficient Structured Orthogonal Parametrization. CoRR (2024)
Paul Mangold, Sergey Samsonov, Safwan Labbi, Ilya Levin, Réda Alami, Alexey Naumov, Eric Moulines
SCAFFLSA: Quantifying and Eliminating Heterogeneity Bias in Federated Linear Stochastic Approximation and Temporal Difference Learning. CoRR (2024)
Nikita Morozov, Daniil Tiapkin, Sergey Samsonov, Alexey Naumov, Dmitry Vetrov
Improving GFlowNets with Monte Carlo Tree Search. CoRR (2024)
Sergey Samsonov, Daniil Tiapkin, Alexey Naumov, Eric Moulines
Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability. COLT (2024)
Denis Belomestny, Artur Goldman, Alexey Naumov, Sergey Samsonov
Theoretical guarantees for neural control variates in MCMC. Math. Comput. Simul. 220 (2024)
Daniil Tiapkin, Nikita Morozov, Alexey Naumov, Dmitry P. Vetrov
Generative Flow Networks as Entropy-Regularized RL. CoRR (2023)
Aleksandr Beznosikov, Sergey Samsonov, Marina Sheshukova, Alexander V. Gasnikov, Alexey Naumov, Eric Moulines
First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities. NeurIPS (2023)
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard
Demonstration-Regularized RL. CoRR (2023)
Aleksandr Beznosikov, Sergey Samsonov, Marina Sheshukova, Alexander V. Gasnikov, Alexey Naumov, Eric Moulines
First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities. CoRR (2023)
Sergey Samsonov, Daniil Tiapkin, Alexey Naumov, Eric Moulines
Finite-Sample Analysis of the Temporal Difference Learning. CoRR (2023)
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Pierre Perrault, Yunhao Tang, Michal Valko, Pierre Ménard
Fast Rates for Maximum Entropy Exploration. CoRR (2023)
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard
Model-free Posterior Sampling via Learning Rate Randomization. CoRR (2023)
Denis Belomestny, Artur Goldman, Alexey Naumov, Sergey Samsonov
Theoretical guarantees for neural control variates in MCMC. 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)
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Pierre Perrault, Yunhao Tang, Michal Valko, Pierre Ménard
Fast Rates for Maximum Entropy Exploration. ICML (2023)
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard
Model-free Posterior Sampling via Learning Rate Randomization. NeurIPS (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)
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Mark Rowland, Michal Valko, Pierre Ménard
Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees. NeurIPS (2022)
Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov
Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation. CoRR (2022)
Sergey Samsonov, Evgeny Lagutin, Marylou Gabrié, Alain Durmus, Alexey Naumov, Eric Moulines
Local-Global MCMC kernels: the best of both worlds. NeurIPS (2022)
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Mark Rowland, Michal Valko, Pierre Ménard
Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees. CoRR (2022)
Daniil Tiapkin, Denis Belomestny, Eric Moulines, Alexey Naumov, Sergey Samsonov, Yunhao Tang, Michal Valko, Pierre Ménard
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses. CoRR (2022)
Daniil Tiapkin, Denis Belomestny, Eric Moulines, Alexey Naumov, Sergey Samsonov, Yunhao Tang, Michal Valko, Pierre Ménard
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses. ICML (2022)
Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov, Kevin Scaman, Hoi-To Wai
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize. NeurIPS (2021)
Denis Belomestny, Leonid Iosipoi, Eric Moulines, Alexey Naumov, Sergey Samsonov
Variance Reduction for Dependent Sequences with Applications to Stochastic Gradient MCMC. SIAM/ASA J. Uncertain. Quantification 9 (2) (2021)
Evgeny Lagutin, Daniil Selikhanovych, Achille Thin, Sergey Samsonov, Alexey Naumov, Denis Belomestny, Maxim Panov, Eric Moulines
MCMC: Sampling through Exploration Exploitation. CoRR (2021)
Denis Belomestny, Ilya Levin, Eric Moulines, Alexey Naumov, Sergey Samsonov, Veronika Zorina
Model-free policy evaluation in Reinforcement Learning via upper solutions. CoRR (2021)
Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov, Kevin Scaman, Hoi-To Wai
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize. CoRR (2021)
Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov, Hoi-To Wai
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning. COLT (2021)
Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov, Hoi-To Wai
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning. CoRR (2021)
Maxim Kaledin, Eric Moulines, Alexey Naumov, Vladislav Tadic, Hoi-To Wai
Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise. CoRR (2020)
Denis Belomestny, Leonid Iosipoi, Eric Moulines, Alexey Naumov, Sergey Samsonov
Variance reduction for Markov chains with application to MCMC. Stat. Comput. 30 (4) (2020)
Maxim Kaledin, Eric Moulines, Alexey Naumov, Vladislav Tadic, Hoi-To Wai
Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise. COLT (2020)
Denis Belomestny, Leonid Iosipoi, Eric Moulines, Alexey Naumov, Sergey Samsonov
Variance reduction for Markov chains with application to MCMC. CoRR (2019)
Scott A. Ochsner, Yolanda F. Darlington, Apollo McOwiti, Wasula H. Kankanamge, Alexey Naumov, Lauren B. Becnel, Neil J. McKenna
A FAIR-Based Approach to Enhancing the Discovery and Re-Use of Transcriptomic Data Assets for Nuclear Receptor Signaling Pathways. Data Sci. J. 16 (2017)
Yolanda F. Darlington, Alexey Naumov, Apollo McOwiti, Wasula H. Kankanamge, Lauren B. Becnel, Neil J. McKenna
Improving the discoverability, accessibility, and citability of omics datasets: a case report. J. Am. Medical Informatics Assoc. 24 (2) (2017)
Scott A. Ochsner, Yolanda F. Darlington, Apollo McOwiti, Wasula H. Kankanamge, Alexey Naumov, Lauren B. Becnel, Neil J. McKenna
A FAIR-Based Approach to Enhancing the Discovery and Re-Use of Transcriptomic Data Assets for Nuclear Receptor Signaling Pathways. Data Sci. J. 16 (2017)