Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/243768
Title: | FUNDAMENTAL PERFORMANCE LIMITS OF STATISTICAL PROBLMES: FROM HYPOTHESIS TESTING TO THE LOTTERY TICKETS HYPOTHESIS | Authors: | PAN JIACHUN | ORCID iD: | orcid.org/0000-0002-7573-0222 | Keywords: | fundamental limits, sequential hypothesis testing, error exponents, Nash equilibrium, self-supervised learning, lottery ticket hypothesis | Issue Date: | 20-Mar-2023 | Citation: | PAN JIACHUN (2023-03-20). FUNDAMENTAL PERFORMANCE LIMITS OF STATISTICAL PROBLMES: FROM HYPOTHESIS TESTING TO THE LOTTERY TICKETS HYPOTHESIS. ScholarBank@NUS Repository. | Abstract: | Understanding the fundamental limits of various statistical problems is of paramount importance. As machine learning continues to evolve, it is critical to understand fundamental limits in the context of new problems. In this thesis, we investigate fundamental performance limits in three problems that have emerged with the rise of machine learning. These problems are sequential composite hypothesis testing, sequential adversarial hypothesis testing game, and explaining the mask-reconstruction-based self-supervised learning using the lottery ticket hypothesis. For sequential composite hypothesis testing, we obtain its first-order and second-order asymptotics of type-I and type-II error probabilities under probabilistic constraints. In sequential adversarial hypothesis testing game, we evaluate the asymptotic Nash equilibrium between the decision maker and the adversary and identify the payoff at this equilibrium. Finally, by leveraging the lottery ticket hypothesis, we theoretically explain the effectiveness of feature learning in mask-reconstruction-based self-supervised learning and derive its performance bound on downstream classification tasks. | URI: | https://scholarbank.nus.edu.sg/handle/10635/243768 |
Appears in Collections: | Ph.D Theses (Open) |
Show full item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
PanJC.pdf | 6.95 MB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.