Folgen
Sergey Samsonov
Sergey Samsonov
HSE university, Moscow
Bestätigte E-Mail-Adresse bei hse.ru - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Variance reduction for Markov chains with application to MCMC
D Belomestny, L Iosipoi, E Moulines, A Naumov, S Samsonov
Statistics and Computing 30, 973-997, 2020
272020
On the stability of random matrix product with markovian noise: Application to linear stochastic approximation and td learning
A Durmus, E Moulines, A Naumov, S Samsonov, HT Wai
Conference on Learning Theory, 1711-1752, 2021
252021
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
A Durmus, E Moulines, A Naumov, S Samsonov, K Scaman, HT Wai
Advances in Neural Information Processing Systems 34, 30063-30074, 2021
242021
Finite-Time High-Probability Bounds for Polyak–Ruppert Averaged Iterates of Linear Stochastic Approximation
A Durmus, E Moulines, A Naumov, S Samsonov
Mathematics of Operations Research, 2024
212024
Rates of convergence for density estimation with generative adversarial networks
N Puchkin, S Samsonov, D Belomestny, E Moulines, A Naumov
Journal of Machine Learning Research 25 (29), 1-47, 2024
18*2024
Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations
D Belomestny, A Naumov, N Puchkin, S Samsonov
Neural Networks 161, 242-253, 2023
182023
Local-Global MCMC kernels: the best of both worlds
S Samsonov, E Lagutin, M Gabrié, A Durmus, A Naumov, E Moulines
Advances in Neural Information Processing Systems 35, 5178-5193, 2022
18*2022
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses
D Tiapkin, D Belomestny, É Moulines, A Naumov, S Samsonov, Y Tang, ...
International Conference on Machine Learning, 21380-21431, 2022
172022
First order methods with markovian noise: from acceleration to variational inequalities
A Beznosikov, S Samsonov, M Sheshukova, A Gasnikov, A Naumov, ...
Advances in Neural Information Processing Systems 36, 2024
152024
Variance reduction for dependent sequences with applications to stochastic gradient MCMC
D Belomestny, L Iosipoi, E Moulines, A Naumov, S Samsonov
SIAM/ASA Journal on Uncertainty Quantification 9 (2), 507-535, 2021
122021
Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability
S Samsonov, D Tiapkin, A Naumov, E Moulines
The Thirty Seventh Annual Conference on Learning Theory, 4511-4547, 2024
7*2024
Variance reduction for additive functionals of Markov chains via martingale representations
D Belomestny, E Moulines, S Samsonov
Statistics and Computing 32 (1), 1-22, 2022
72022
Queuing dynamics of asynchronous Federated Learning
L Leconte, M Jonckheere, S Samsonov, E Moulines
International Conference on Artificial Intelligence and Statistics, 1711-1719, 2024
52024
Br-snis: bias reduced self-normalized importance sampling
G Cardoso, S Samsonov, A Thin, E Moulines, J Olsson
Advances in Neural Information Processing Systems 35, 716-729, 2022
52022
Theoretical guarantees for neural control variates in MCMC
D Belomestny, A Goldman, A Naumov, S Samsonov
Mathematics and Computers in Simulation 220, 382-405, 2024
42024
Rosenthal-type inequalities for linear statistics of Markov chains
A Durmus, E Moulines, A Naumov, S Samsonov, M Sheshukova
arXiv preprint arXiv:2303.05838, 2023
42023
Probability and moment inequalities for additive functionals of geometrically ergodic Markov chains
A Durmus, E Moulines, A Naumov, S Samsonov
Journal of Theoretical Probability, 1-50, 2024
32024
Estimation of the second moment based on rounded data
SV Samsonov, NG Ushakov, VG Ushakov
Journal of Mathematical Sciences 237, 819-825, 2019
22019
Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning
S Samsonov, E Moulines, QM Shao, ZS Zhang, A Naumov
arXiv preprint arXiv:2405.16644, 2024
12024
Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
T Gritsaev, N Morozov, S Samsonov, D Tiapkin
arXiv preprint arXiv:2410.15474, 2024
2024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20