University of Cambridge > Talks.cam > Machine learning in Physics, Chemistry and Materials discussion group (MLDG) > Solving the electronic Schrödinger equation with deep learning

Solving the electronic Schrödinger equation with deep learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Bingqing Cheng .

Variational quantum Monte Carlo provides a computationally efficient platform for arbitrarily accurate solutions of the electronic Schrödinger equation, but until recently the accuracy has been limited by the expressiveness of the available wave function ansatzes [1]. In this talk, I will present our deep-learning ansatz PauliNet [2], which takes advantage of deep neural networks as universal approximators to represent electronic wave functions with high fidelity. PauliNet uses a baseline HF solution and deep Jastrow factor and backflow transformation, and reaches state-of-the-art accuracy for systems ranging from diatomic molecules, to strongly correlated H₁₀, to cyclobutadiene (28 electrons). I will also discuss the similarities and differences of PauliNet to the FermiNet ansatz, which is another deep-learning ansatz [3].

1. Foulkes, W. M. C., Mitas, L., Needs, R. J. & Rajagopal, G. Rev. Mod. Phys. 73, 33–83 (2001). https://doi.org/10.1103/RevModPhys.73.33

2. Hermann, J., Schätzle, Z. & Noé, F. Nat. Chem. (2020). https://doi.org/10.1038/s41557-020-0544-y

3. Pfau, D., Spencer, J. S., Matthews, A. G. de G. & Foulkes, W. M. C. Phys. Rev. Research 2, 033429 (2020). https://doi.org/10.1103/PhysRevResearch.2.033429

This talk is part of the Machine learning in Physics, Chemistry and Materials discussion group (MLDG) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity