Practicum Experience(s)
Lawrence Berkeley National Laboratory (2024)
Summary of Research
I work on in inverse problems and uncertainty quantification, with applications in medical and atmospheric imaging. Currently, under the mentorship of Julianne and Tia Chung, I am working with autoencoder networks that can supplement traditional inverse problem techniques (in UQ and regularization, for example). More broadly in my research, and throughout my PhD, I hope to learn more methodologies of numerical linear algebra and ways that they can be applied to solve problems in engineering and sustainability.
Annual Program Review Abstracts
Publications
E. Hart, J. Chung, and M. Chung, A paired autoencoder framework for inverse problems via Bayes risk minimization, 2025 (Preprint)
S. H. Lim, Y. Wang, A. Yu, E. Hart, M. W. Mahoney, X. S. Li, and N. B. Erichson, Elucidating the design choice of probability paths in flow matching for forecasting, 2025 (Preprint)
M. Chung, E. Hart, J. Chung, B. Peters, and E. Haber, Paired autoencoders for likelihood-free estimation in inverse problems, Machine Learning: Science and Technology, 5 (2024), p. 045055
E. Buser, E. Hart, and B. Huenemann, Comparison of atlas-based and neural-network-based semantic segmentation for dense MRI images, SIAM Undergraduate Research Online, 15 (2022)
Awards
Women in Natural Sciences Fellowship, Emory University (2022-Present)
Dean's Award for Academic Excellence with Distinction, Colgate University (2018-2022)
Graduate School Access Fund Recipient, Colgate University (2021)
Osborne Mathematics Prize, Colgate University (2021)
Sisson Mathematics Prize, Colgate University (2020)
Charles A. Dana Scholar, Colgate University (2020)
Liberal Arts Core Curriculum Prize, Colgate University (2019)