2026-09-19T04:44:01Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1554062024-06-28T03:33:50Zcom_1721.1_7582com_1721.1_7581col_1721.1_131024
Soljačić, Marin
Dugan, Owen Michael
Massachusetts Institute of Technology. Department of Physics
2024-06-27T19:51:13Z
2024-06-27T19:51:13Z
2024-05
2024-05-20T16:12:30.018Z
https://hdl.handle.net/1721.1/155406
0000-0002-9249-3660
In this thesis, we explore the application of machine learning (ML) methods to problems in physics.
Because ML has revolutionized a wide range of fields, it is natural to ask whether it may be a valuable tool for physics. Physics applications present a challenge as many physics problems have a precise mathematical definition and a classical (non-ML-based) solution, making ML models less likely to outperform existing techniques.
In this paper, we focus on two general problems for which ML techniques provide an improvement as compared to existing techniques in physics: 1) fast simulation, and 2) discovering new physics. To illustrate the potential of ML to advance physics by solving these problems, we develop a physics-optimized ML model for each of the problems identified above, respectively: 1) Q-Flow, a technique for faster bosonic quantum simulation using normalizing flows to simulate a compressed representation of a quantum state, and 2) OccamNet, a framework for scientific discovery through novel algorithms for efficient and parallelizable symbolic regression. Our methods demonstrate the potential for ML as a valuable tool for physics research.
S.B.
Massachusetts Institute of Technology
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
https://creativecommons.org/licenses/by-nc-nd/4.0/
Machine Learning for Physics: from Symbolic Regression to Quantum Simulation
Thesis
application/pdf
Bachelor
Bachelor of Science in Physics
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="791c9fce-7b44-4290-8ba1-2c822cfe9847">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Machine Learning for Physics: from Symbolic Regression to Quantum Simulation</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2024-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Dugan, Owen Michael</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://creativecommons.org/licenses/by-nc-nd/4.0/</License>
<Abstract>In this thesis, we explore the application of machine learning (ML) methods to problems in physics.
Because ML has revolutionized a wide range of fields, it is natural to ask whether it may be a valuable tool for physics. Physics applications present a challenge as many physics problems have a precise mathematical definition and a classical (non-ML-based) solution, making ML models less likely to outperform existing techniques.
In this paper, we focus on two general problems for which ML techniques provide an improvement as compared to existing techniques in physics: 1) fast simulation, and 2) discovering new physics. To illustrate the potential of ML to advance physics by solving these problems, we develop a physics-optimized ML model for each of the problems identified above, respectively: 1) Q-Flow, a technique for faster bosonic quantum simulation using normalizing flows to simulate a compressed representation of a quantum state, and 2) OccamNet, a framework for scientific discovery through novel algorithms for efficient and parallelizable symbolic regression. Our methods demonstrate the potential for ML as a valuable tool for physics research.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>