Electronic Structure Reading Group: Multitask Surrogate Models for Heterogeneous Electronic Structures Data


Event details

Date 10.06.2024
Hour 16:0017:30
Speaker Katharine Fisher (MIT)
Category Conferences - Seminars
Event Language English

Physical data is increasingly openly accessible though it may be challenging to definitively rank the accuracy of different information sources. We demonstrate that multitask Gaussian process regression can leverage “datasets of opportunity” to efficiently construct surrogate models.

Katharine Fisher, Michael F. Herbst, and Youssef Marzouk. "Multitask methods for predicting molecular properties from heterogeneous data." arXiv preprint arXiv:2401.17898 (2024). https://arxiv.org/abs/2401.17898


The electronic structure reading group brings together researchers and students interested in mathematical aspects of electronic structure problems and adjacent topics, including:

  • Density Functional Theory
  • Many-body Schrödinger equation for electrons
  • Born-Oppenheimer Molecular Dynamics
  • Numerical analysis and error control
For updates, join the matrix chat room at #electronic-structure:epfl.ch (requires a GASPAR account).

Website: https://matmat.org/readinggroup/

Practical information

  • General public
  • Free


  • Muhammad Hassan, EPFL Michael Herbst, EPFL