자료유형  

 학위논문

Control Number  

0016935006

International Standard Book Number  

9798380616409

Dewey Decimal Classification Number  

004

Main Entry-Personal Name  

Liu, Chong.

Publication, Distribution, etc. (Imprint  

[S.l.] : University of California, Santa Barbara., 2023

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2023

Physical Description  

1 online resource(194 p.)

General Note  

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

General Note  

Advisor: Wang, Yu-Xiang.

Dissertation Note  

Thesis (Ph.D.)--University of California, Santa Barbara, 2023.

Restrictions on Access Note  

This item must not be sold to any third party vendors.

Summary, Etc.  

요약Deep neural networks usually have many hyperparameters that need to be tuned. Modern material design problems usually require material scientists to sequentially select processing parameters and conduct experiments to observe material performances. To save privacy cost, the learning system needs to carefully choose queries to answer under the differential privacy framework. To train a robot under video guidance, engineers need to carefully choose video samples for training. However, in all cases, people cannot observe performances of unselected actions and the experimental cost can be huge. These two challenges hinder efficient neural network training, new material design, privacy protection, and robot training and call for actions. In this thesis, I present my research on optimization, bandits, and active learning under the adaptive sequential decision making framework. My algorithms are able to solve black box function optimization without the curse of dimensionality, achieve no regret under the function class misspecification, reduce privacy cost under the differential privacy framework, and significantly reduce video sample complexity for robot training. All of them come with theoretical or empirical analysis.

Subject Added Entry-Topical Term  

Computer science.

Subject Added Entry-Topical Term  

Information technology.

Index Term-Uncontrolled  

Deep neural networks

Index Term-Uncontrolled  

Privacy framework

Index Term-Uncontrolled  

Privacy protection

Index Term-Uncontrolled  

Decision making

Index Term-Uncontrolled  

Bandit optimization

Added Entry-Corporate Name  

University of California, Santa Barbara Computer Science

Host Item Entry  

Dissertations Abstracts International. 85-04B.

Host Item Entry  

Dissertation Abstract International

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:640727