Learning normalizing flows from Entropy-Kantorovich potentials
We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows are cast as gradients of scalar potential functions. This formulation allows us to train a dual objective comprised only of the scalar potential functions, and removes the burden of explicitly computing normalizing flows during training. After training, the normalizing flow is easily recovered from the potential functions.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Hellinger-Kantorovich Gradient Flows: Global Exponential Decay of Entropy Functionals
We investigate a family of gradient flows of positive and probability measures, focusing on the Hellinger-Kantorovich (HK) geometry, which unifies transport mechanism of Otto-Wasserstein, and the birth-death mechanism of…
Inference OptimizationOn the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy
Gradient-flow sampling interprets a Gibbs distribution as the minimizer of an energy functional over probability measures and generates dynamics converging to this target. Under spherical Hellinger-Kantorovich (SHK) geom…
Conditional normalizing flows for IceCube event reconstruction
The IceCube Neutrino Observatory is a cubic-kilometer high-energy neutrino detector deployed in the Antarctic ice. Two major event classes are charged-current electron and muon neutrino interactions. In this contribution…
Amortized Optimal Transport from Sliced Potentials
We propose a novel amortized optimization method for predicting optimal transport (OT) plans across multiple pairs of measures by leveraging Kantorovich potentials derived from sliced OT. We introduce two amortization st…
Bayesian Active Learning By Distribution Disagreement
Active Learning (AL) for regression has been systematically under-researched due to the increased difficulty of measuring uncertainty in regression models. Since normalizing flows offer a full predictive distribution ins…
Active LearningregressionUncertainty Quantification