Density Functional Theory I: DFT in the Era of Machine Learning and AI

Presentations

• A Tale of Two Splines: Towards Next-Generation Density Functionals and Machine Learning for Chemistry

  Invited-In-person · Invited

  March 16, 2026, 8:00 AM – March 16, 2026, 8:36 AM

  Publication: Z. M. Sparrow, B. G. Ernst, T. K. Quady, and R. A. DiStasio Jr., Uniting Non-Empirical and Empirical Density Functional Approximation Strategies Using Constraint-Based Regularization, J. Phys. Chem. Lett. 13, 6896-6904 (2022).
  
  Z. Shen, Y. Yang, Z. M. Sparrow, B. G. Ernst, T. K. Quady, R. Kang, J. Lee, Y. Yang, L. Tu, and R. A. DiStasio Jr., Learning Molecular Conformational Energies Using Semi-Local Density Fingerprints, J. Phys. Chem. Lett. in press (2025).

  Presenters

  • Robert Distasio

    • Cornell University

  Authors

  • Robert Distasio

    • Cornell University

  View abstract →

• Application of Machine-Learned Exchange-Correlation Functionals to Surface Chemistry

  Oral-In-person

  March 16, 2026, 8:36 AM – March 16, 2026, 8:48 AM

  Presenters

  • Mohamed Abdallah

    • Harvard University

  Authors

  • Mohamed Abdallah

    • Harvard University

  • Zhuotao Jin

  • Kyle Bystrom

  • Boris Kozinsky

    • Harvard University

  View abstract →

• What If Machine Learning Could Learn the Electrons Too? Towards ML-Enhanced DFTB for Electronic Structure Prediction

  Oral-In-person

  March 16, 2026, 8:48 AM – March 16, 2026, 9:00 AM

  Presenters

  • Filippo Balzaretti

    • University of California, Santa Cruz

  Authors

  • Filippo Balzaretti

    • University of California, Santa Cruz

  • Marcos Calegari Andrade

    • University of California, Santa Cruz

  View abstract →

• Learning local and semi-local density functionals from exact exchange-correlation potentials and energies

  Oral-In-person

  March 16, 2026, 9:00 AM – March 16, 2026, 9:12 AM

  Presenters

  • Bikash Kanungo

    • University of Michigan

  Authors

  • Bikash Kanungo

    • University of Michigan

  • Jefrrey Hatch

  • Paul Zimmerman

  • Vikram Gavini

    • University of Michigan

  View abstract →

• Reconstructing atomic geometries from concise local representations

  Oral-In-person

  March 16, 2026, 9:12 AM – March 16, 2026, 9:24 AM

  Presenters

  • Jigyasa Nigam

    • Massachusetts Institute of Technology

  Authors

  • Jigyasa Nigam

    • Massachusetts Institute of Technology

  • Tess Smidt

    • Massachusetts Institute of Technology

  • Tuong Phung

    • Massachusetts Institute of Technology

  View abstract →

• Machine learning of nonlocal exchange-correlation functionals

  Invited-In-person · Invited

  March 16, 2026, 9:24 AM – March 16, 2026, 10:00 AM

  Publication: (1) Bystrom, K.; Falletta, S.; Kozinsky, B. Training Machine-Learned Density Functionals on Band Gaps. J. Chem. Theory Comput. 2024, 20 (17), 7516–7532. https://doi.org/10.1021/acs.jctc.4c00999.
  (2) Bystrom, K.; Kozinsky, B. CIDER: An Expressive, Nonlocal Feature Set for Machine Learning Density Functionals with Exact Constraints. J. Chem. Theory Comput. 2022, acs.jctc.1c00904. https://doi.org/10.1021/acs.jctc.1c00904.
  (3) Bystrom, K.; Kozinsky, B. Nonlocal Machine-Learned Exchange Functional for Molecules and Solids. Phys. Rev. B 2024, 110 (7), 075130. https://doi.org/10.1103/PhysRevB.110.075130.

  Presenters

  • Boris Kozinsky

    • Harvard University

  Authors

  • Boris Kozinsky

    • Harvard University

  • Kyle Bystrom

    • Flatiron Institute

  • Zhuotao Jin

  • Mohamed Abdallah

    • Harvard University

  View abstract →

• High-Throughput Calculations of Spectroscopic Properties of Solids using Optimally-Tuned Screened Range-Separated Hybrid Functionals

  Oral-In-person

  March 16, 2026, 10:00 AM – March 16, 2026, 10:12 AM

  Presenters

  • Brian Xiao

    • University of California, Berkeley

  Authors

  • Brian Xiao

    • University of California, Berkeley

  • Stephen Gant

    • University of California, Berkeley

  • Francesco Ricci

    • UClouvain

  • Yasaman Bahri

    • Google DeepMind

  • Leeor Kronik

    • Weizmann Institute of Science

  • Jeffrey Neaton

    • University of California, Berkeley

  View abstract →

• Machine learning empirical pseudopotentials for total energy and electronic energy bands

  Oral-In-person

  March 16, 2026, 10:12 AM – March 16, 2026, 10:24 AM

  Publication: S. Kang, R. Kim, S. Han and Y.-W. Son, APL Mach. Learn. 3, 036108 (2025)

  Presenters

  • Sungmo Kang

    • Korea Institute for Advanced Study

  Authors

  • Sungmo Kang

    • Korea Institute for Advanced Study

  • Rokyeon Kim

    • Korea Institute for Advanced Study

  • Seungwu Han

    • Seoul National University

  • Hongkee Yoon

  • Young-Woo Son

    • Korea Institute for Advanced Study

  View abstract →

• Physics-Informed Neural Operator Inversion Tools for Improved Density Functional Theory

  Oral-In-person

  March 16, 2026, 10:24 AM – March 16, 2026, 10:36 AM

  Presenters

  • Bridget Sprecher

    • University of California, Merced

  Authors

  • Bridget Sprecher

    • University of California, Merced

  • Vincent Martinetto

    • University of California, Merced

  • Karan Shah

    • Helmholtz Zentrum Dresden-Rossendorf

  • Mani Lokamani

    • Helmholtz-Zentrum Dresden-Rossendorf

  • Attila Cangi

    • Helmholtz Zentrum Dresden-Rossendorf

  • Aurora Pribram-Jones

    • University of California, Merced

  View abstract →

• Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution

  Oral-In-person

  March 16, 2026, 10:36 AM – March 16, 2026, 10:48 AM

  Publication: Accepted to AI4Mat-NeurIPS 2025

  Presenters

  • Pranav Kakhandiki

    • Stanford University

  Authors

  • Pranav Kakhandiki

    • Stanford University

  • Sean Gasiorowski

    • SLAC National Accelerator Laboratory

  • Daniel Ratner

    • Stanford University

  View abstract →

• Machine-Learning Interatomic Potentials for Charge-Density-Wave Phases in mono- and bilayers NbSe₂

  Oral-In-person

  March 16, 2026, 10:48 AM – March 16, 2026, 11:00 AM

  Publication: Norma Rivano et al. Exploring Charge Density Waves in NbSe₂ with Machine Learning arXiv.2504.13675 (2025)

  Presenters

  • Norma Rivano

    • Harvard University

  Authors

  • Norma Rivano

    • Harvard University

  • Francesco Libbi

    • Harvard University

  • Chuin Wei Tan

    • Harvard University

  • Christopher Cheung

  • Jose Lado

    • Aalto University

  • Arash Mostofi

    • Imperial College London

  • Philip Kim

    • Harvard University

  • Johannes Lischner

    • Imperial College London

  • Adolfo Fumega

    • Aalto University

  • Boris Kozinsky

    • Harvard University

  • Zachary Goodwin

    • University of Oxford

  View abstract →