48 min
Seminar, Hosted by Simons Institute for the Theory of Computing
Normalizing Flow Maps
Imperial College London
Recording
Abstract
Normalizing Flow Maps learn invertible transports between arbitrary pairs of times while retaining exact density evaluation. This combines few-step generation with likelihoods and sampling in both temporal directions. The talk develops pointwise and distributional consistency objectives, including forward and reverse KL formulations, connecting flow-map regression with likelihood training. Image-generation experiments and equilibrium sampling of small peptides test the approach against earlier normalizing-flow methods.