Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

Authors: Takeshi Teshima, Isao Ishikawa, Koichi Tojo, Kenta Oono, Masahiro Ikeda, Masashi Sugiyama

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We answer this question by showing a convenient criterion: a CF-INN is universal if its layers contain affine coupling and invertible linear functions as special cases. As its corollary, we can affirmatively resolve a previously unsolved problem: whether normalizing flow models based on affine coupling can be universal distributional approximators. In the course of proving the universality, we prove a general theorem to show the equivalence of the universality for certain diffeomorphism classes, a theoretical insight that is of interest by itself.
Researcher Affiliation Academia Takeshi Teshima The University of Tokyo, RIKEN teshima@ms.k.u-tokyo.ac.jp Isao Ishikawa* Ehime University, RIKEN ishikawa.isao.zx@ehime-u.ac.jp Koichi Tojo RIKEN koichi.tojo@riken.jp Kenta Oono The University of Tokyo kenta_oono@mist.i.u-tokyo.ac.jp Masahiro Ikeda RIKEN masahiro.ikeda@riken.jp Masashi Sugiyama RIKEN, The University of Tokyo sugi@k.u-tokyo.ac.jp
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access information (e.g., specific repository link, explicit statement of code release) for the source code of the methodology described.
Open Datasets No The paper is theoretical and does not describe experiments that use training datasets. Therefore, it does not provide concrete access information for a publicly available or open dataset used for training.
Dataset Splits No The paper is theoretical and does not describe experiments that involve dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe experiments that would require specific hardware, therefore no hardware specifications are provided.
Software Dependencies No The paper is theoretical and does not mention specific ancillary software details with version numbers needed to replicate experiments.
Experiment Setup No The paper is theoretical and does not describe experiments, thus no experimental setup details like hyperparameters or training configurations are provided.