- Seminar Calendar
- Seminar Archive
- 2024-2025 Semester 1
- 2023-2024 Semester 2
- 2023-2024 Semester 1
- 2022-2023 Semester 2
- 2022-2023 Semester 1
- 2021-2022 Semester 2
- 2021-2022 Semester 1
- 2020-2021 Semester 2
- 2020-2021 Semester 1
- 2019-2020 Semester 2
- 2019-2020 Semester 1
- 2018-2019 Semester 2
- 2018-2019 Semester 1
- 2017-2018 Semester 2
- 2017-2018 Semester 1
- 2016-2017 Semester 2
- 2016-2017 Semester 1
- 2015-2016 Semester 1
- 2015-2016 Semester 2
- 2014-2015 Semester 2
- 2014-2015 Semester 1
- 2013-2014 Semester 2
- 2013-2014 Semester 1
- 2012-2013 Semester 2
- 2012-2013 Semester 1
- 2011-2012 Semester 2
- 2011-2012 Semester 1
- 2010-2011 Semester 2
- 2010-2011 Semester 1
- 2009-2010 Semester 2
- 2009-2010 Semester 1
- 2008-2009 Semester 2
- 2008-2009 Semester 1
- 2007-2008 Semester 2
- 2007-2008 Semester 1
- 2006-2007 Semester 2
- 2006-2007 Semester 1
- 2005-2006 Semester 2
- 2005-2006 Semester 1
- Contact
- Site Map
Seminar: Normal approximation and multiplier bootstrap for Linear Stochastic Approximation
----------------------------------------------------------------------------------------------------
Department of Systems Engineering and Engineering Management
The Chinese University of Hong Kong
----------------------------------------------------------------------------------------------------
Date: Monday, December 2, 2024, 4:30 pm HKT
Venue: ERB 513, The Chinese University of Hong Kong
Title: Normal approximation and multiplier bootstrap for Linear Stochastic Approximation
Speaker: Dr. Sergey Samsonov, HSE University, Moscow, Russia
Abstract:
In this talk, we obtain the Berry-Esseen bound for multivariate normal approximation for the Polyak-Ruppert averaged iterates of the linear stochastic approximation (LSA) algorithm with decreasing step size. Moreover, we prove the non-asymptotic validity of the confidence intervals for parameter estimation with LSA based on multiplier bootstrap. This procedure updates the LSA estimate together with a set of randomly perturbed LSA estimates upon the arrival of subsequent observations. We also study the setting of LSA with Markov noise and show a non-asymptotic validity of multiplier block-bootstrap method.
Biography:
Sergey Samsonov is a research fellow at the International Laboratory of Stochastic Algorithms and High-Dimensional Inference of the HSE University, Moscow, Russia. He obtained his PhD degree in mathematics from HSE University in 2024. Sergey's research interests mainly revolve around stochastic approximation, sampling methods, and generative modeling. His primary research focus is the probabilistic inference for stochastic approximation algorithms and their applications in reinforcement learning. Sergey Samsonov has authored 17 papers in leading journals and conferences in the field, including COLT, ICML, NeurIPS, AISTATS, Journal of Machine Learning Research, Mathematics of Operations Research.
Everyone is welcome to attend the talk!
SEEM-5201 Website: https://seminar.se.cuhk.edu.hk
Email: seem5201@se.cuhk.edu.hk
Date:
Monday, December 2, 2024 - 16:30 to 17:30