東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Monte Carlo Tree Methods for Nonline...

Zhai, Yaoguang.

Linked to FindBook

Google Book

Amazon

博客來

Monte Carlo Tree Methods for Nonlinear Optimization.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Monte Carlo Tree Methods for Nonlinear Optimization./
Author:	Zhai, Yaoguang.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
Description:	176 p.
Notes:	Source: Dissertations Abstracts International, Volume: 85-10, Section: B.
Contained By:	Dissertations Abstracts International85-10B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30994656
ISBN:	9798382303819

Monte Carlo Tree Methods for Nonlinear Optimization.
Zhai, Yaoguang.

Monte Carlo Tree Methods for Nonlinear Optimization. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 176 p.

Source: Dissertations Abstracts International, Volume: 85-10, Section: B.

Thesis (Ph.D.)--University of California, San Diego, 2024.

As highly nonlinear continuous functions become the prevalent model of computation, NP-hard optimization problems over the continuous domain pose significant challenges to AI/ML algorithms and systems, especially in terms of their robustness and safety. The key to nonlinear optimization is to efficiently search through input regions with potentially widely varying numerical properties to achieve low-regret descent and fast progress toward the optima. Monte Carlo Tree Search (MCTS) methods have recently been introduced to improve global optimization by computing better partitioning of the search space that balances exploration and exploitation.This dissertation investigates the application of Monte Carlo tree methods for nonlinear optimization (encompassing black-box and non-convex optimization) to identify the global optimum, and the crafting of training datasets designed to boost transferability and reduce dataset size in computational molecular dynamics. To tackle global optimization challenges, the study integrates sampling strategies with MCTS frameworks, employing diverse local optimization techniques to highlight promising samples. These techniques span stochastic search, Gaussian Processes regression, numerical overapproximation of the objective function, and analysis of first- and second-order information. In the realm of training dataset development, computational simulations of water serve as a practical case study. An active learning framework is introduced to efficiently condense the size of the training dataset while preserving its quality and comprehensiveness. The research further explores model transferability by assessing various subsets for training set inclusion to the simulation of water molecules, thereby uncovering the model's adaptability challenges across different scenarios.The findings affirm that Monte Carlo tree methods provide cost-effective strategies for managing the complexities inherent in state space exploration. By applying these methods to a range of application areas, the dissertation underscores the robustness and utility of sampling techniques in advancing machine learning research.

ISBN: 9798382303819Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Global optimization

Monte Carlo Tree Methods for Nonlinear Optimization.
LDR:03319nmm a2200385 4500 001 2398167
005 20240812064355.5
006 m o d
007 cr#unu||||||||
008 251215s2024 ||||||||||||||||| ||eng d
020 $a 9798382303819
035 $a (MiAaPQ)AAI30994656
035 $a AAI30994656
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhai, Yaoguang. $3 3768076
245 1 0 $a Monte Carlo Tree Methods for Nonlinear Optimization.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 176 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-10, Section: B.
500 $a Advisor: Gao, Sicun;Paesani, Francesco.
502 $a Thesis (Ph.D.)--University of California, San Diego, 2024.
520 $a As highly nonlinear continuous functions become the prevalent model of computation, NP-hard optimization problems over the continuous domain pose significant challenges to AI/ML algorithms and systems, especially in terms of their robustness and safety. The key to nonlinear optimization is to efficiently search through input regions with potentially widely varying numerical properties to achieve low-regret descent and fast progress toward the optima. Monte Carlo Tree Search (MCTS) methods have recently been introduced to improve global optimization by computing better partitioning of the search space that balances exploration and exploitation.This dissertation investigates the application of Monte Carlo tree methods for nonlinear optimization (encompassing black-box and non-convex optimization) to identify the global optimum, and the crafting of training datasets designed to boost transferability and reduce dataset size in computational molecular dynamics. To tackle global optimization challenges, the study integrates sampling strategies with MCTS frameworks, employing diverse local optimization techniques to highlight promising samples. These techniques span stochastic search, Gaussian Processes regression, numerical overapproximation of the objective function, and analysis of first- and second-order information. In the realm of training dataset development, computational simulations of water serve as a practical case study. An active learning framework is introduced to efficiently condense the size of the training dataset while preserving its quality and comprehensiveness. The research further explores model transferability by assessing various subsets for training set inclusion to the simulation of water molecules, thereby uncovering the model's adaptability challenges across different scenarios.The findings affirm that Monte Carlo tree methods provide cost-effective strategies for managing the complexities inherent in state space exploration. By applying these methods to a range of application areas, the dissertation underscores the robustness and utility of sampling techniques in advancing machine learning research.
590 $a School code: 0033.
650 4 $a Computer science. $3 523869
650 4 $a Computational chemistry. $3 3350019
650 4 $a Physical chemistry. $3 1981412
653 $a Global optimization
653 $a Machine learning
653 $a Monte Carlo Tree Search
653 $a Computational simulations
690 $a 0984
690 $a 0219
690 $a 0800
690 $a 0494
710 2 $a University of California, San Diego. $b Computer Science and Engineering. $3 1018473
773 0 $t Dissertations Abstracts International $g 85-10B.
790 $a 0033
791 $a Ph.D.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30994656