Powered by Indico
v3.2.8
Please join us for a Flatiron Institute Computational Methods and Data Science Journal Club with Joan Bruna, Associate Professor with Computer Science, Data Science, and Mathematics at NYU Courant. Joan's talk will take place in the CCN Classroom from 3:00-4:00 PM, and will be followed by a reception in the CCN 4th Floor Pantry from 4:00-5:00 PM.
Title: Separations in symmetric and antisymmetric neural ansatze
Abstract: Many-particle systems appear across several areas of physics and chemistry, and often their governing equations exhibit invariances to particle permutations, motivating the study of function approximation under particle symmetries. For instance, the hamiltonian in classical mechanics is permutation invariant, while the wavefunction in fermionic systems is invariant up to permutation signs. In this talk, we will describe the ability of certain neural network architectures to approximate symmetric and antisymmetric functions. Specifically, we study the approximation benefits of `self-attention' in symmetric networks, and the benefits of the Jastrow ansatz over the simpler Slater determinant, establishing the first quantitative separations. Joint work with Aaron Zweig.