Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference

Shumao Zhang, Thomas Hou, Pengchuan Zhang

Abstract: High-dimensional Bayesian inference problems cast a long-standing challenge in generating samples, especially when the posterior has multiple modes. For a wide class of Bayesian inference problems equipped with the multiscale structure that low-dimensional (coarse-scale) surrogate can approximate the original high-dimensional (fine-scale) problem well, we propose to train a Multiscale Invertible Generative Network (MsIGN) for sample generation. A novel prior conditioning layer is designed to bridge networks at different resolutions, enabling coarse-to-fine multi-stage training. Jeffreys divergence is adopted as the training objective to avoid mode dropping. On two high-dimensional Bayesian inverse problems, MsIGN approximates the posterior accurately and clearly captures multiple modes, showing superior performance compared with previous deep generative network approaches. On the natural image synthesis task, MsIGN achieves the superior performance in bits-per-dimension compared with our baseline models and yields great interpret-ability of its neurons in intermediate layers.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=1ewipEAc8r