Prof. Thomas Miller
Thomas Miller’s research focuses on the development of theoretical and computational methods to study chemical processes that are related to catalysis, battery technologies, and membrane protein biosynthesis. After completing his undergraduate studies at Texas A&M University, he attended graduate school in the UK on a British Marshall Scholarship and received his Ph.D. from Oxford University in 2005. Miller then returned to the US for a postdoctoral fellowship at UC Berkeley. He joined the faculty of the California Institute of Technology in 2008 and was promoted to full professor in 2013. While at Caltech, he has received awards that include the Sloan Research Fellowship, NSF CAREER Award, Associated Students of Caltech Teaching Award, Dreyfus Teacher-Scholar Award, and the ACS Early-Career Award in Theoretical Chemistry.
Quantum Machine Learning for Accurate and Low-Cost Computational Chemistry
Thomas F. Miller III, California Institute of Technology
Quantum mechanical predictions of ground-state and excited-state potential energy surfaces and properties face a punishing balance between prediction accuracy and computational cost, creating demand for new methods and modeling strategies. Machine learning (ML) for electronic structure offers promise in this regard, although conventional approaches require vast amounts of high-quality data and offer limited transferability in chemical space. We describe two frameworks for addressing this challenge: Molecular-Orbital-Based Machine Learning [1-3] and OrbNet . These methods focus on training not with respect to atom-based features, but instead use features based on molecular orbitals, which have no explicit dependence on the underlying atom-types and thus provide greater chemical transferability. Both methods provide striking accuracy and transferability across chemical space while yielding 1000-fold or greater reductions in computational cost. We additionally demonstrate that OrbNet provides a powerful framework for the direct prediction of molecular properties based on experimental datasets.
 “Transferability in machine learning for electronic structure via the molecular orbital basis.” M. Welborn, L. Cheng, and T. F. Miller III, J. Chem. Theory Comput., 14, 4772 (2018).
 “A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules.” L. Cheng, M. Welborn, A. S. Christensen, and T. F. Miller III, J. Chem. Phys., 150, 131103 (2019).
 “Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states.” T. Husch, J. Sun, L. Cheng, S. J. R. Lee, T. F. Miller III. arXiv:2010.03626
 “OrbNet: Deep learning for quantum chemistry using symmetry-adapted atomic-orbital features.” Z. Qiao, M. Welborn, A. Anandkumar, F. R. Manby, and T. F. Miller III, J. Chem. Phys. 153, 124111 (2020).
Prof. Nancy Makri
Nancy Makri received a B.S. in Chemistry from the University of Athens in 1985 and a Ph.D. from the University of California at Berkeley in 1989. After spending two years as a Junior Fellow at Harvard, she joined the University of Illinois at Urbana-Champaign, where she is currently the Edward William and Jane Marr Gutgsell Professor and holds faculty appointments in Chemistry and Physics. Makri’s research focuses on the development of theoretical methods for simulating the quantum dynamics of condensed phase processes. She has pioneered rigorous real-time path integral methods which have helped quantify the interplay among tunneling, quantum interference and thermal fluctuations in chemical kinetics. Makri is the recipient of National Science Foundation and Beckman Young Investigator Awards, the Sloan Research Fellowship, Cottrell and Dreyfus Scholar Awards and the Packard Fellowship for Science and Engineering. She is a Fellow of the American Physical Society and the American Association for the Advancement of Science, and a recipient of the Bodossaki Academic Prize in Physical Sciences. Makri is also a Medalist and a member of the International Academy of Quantum Molecular Science.