Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

An adaptive transport framework for joint and conditional density estimation

Ricardo Baptista 1 Olivier Zahm 2 Youssef Marzouk 1
2 AIRSEA - Mathematics and computing applied to oceanic and atmospheric flows
Inria Grenoble - Rhône-Alpes, UGA - Université Grenoble Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : We propose a general framework to robustly characterize joint and conditional probability distributions via transport maps. Transport maps or "flows" deterministically couple two distributions via an expressive monotone transformation. Yet, learning the parameters of such transformations in high dimensions is challenging given few samples from the unknown target distribution, and structural choices for these transformations can have a significant impact on performance. Here we formulate a systematic framework for representing and learning monotone maps, via invertible transformations of smooth functions, and demonstrate that the associated minimization problem has a unique global optimum. Given a hierarchical basis for the appropriate function space, we propose a sample-efficient adaptive algorithm that estimates a sparse approximation for the map. We demonstrate how this framework can learn densities with stable generalization performance across a wide range of sample sizes on real-world datasets.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas
Contributor : Olivier Zahm <>
Submitted on : Sunday, December 13, 2020 - 7:28:14 PM
Last modification on : Monday, December 14, 2020 - 2:45:34 PM

Links full text


  • HAL Id : hal-03060198, version 1
  • ARXIV : 2009.10303



Ricardo Baptista, Olivier Zahm, Youssef Marzouk. An adaptive transport framework for joint and conditional density estimation. 2020. ⟨hal-03060198⟩



Record views