{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/analyzing-inverse-problems-with-invertible","title":"Analyzing Inverse Problems with Invertible Neural Networks","arxiv_id":"1808.04730","date":"2018-08-14","proceeding":"ICLR 2019 5","authors":["Lynton Ardizzone","Jakob Kruse","Sebastian Wirkert","Daniel Rahner","Eric W. Pellegrini","Ralf S. Klessen","Lena Maier-Hein","Carsten Rother","Ullrich Köthe"],"abstract":"In many tasks, in particular in natural science, the goal is to determine\nhidden system parameters from a set of measurements. Often, the forward process\nfrom parameter- to measurement-space is a well-defined function, whereas the\ninverse problem is ambiguous: one measurement may map to multiple different\nsets of parameters. In this setting, the posterior parameter distribution,\nconditioned on an input measurement, has to be determined. We argue that a\nparticular class of neural networks is well suited for this task -- so-called\nInvertible Neural Networks (INNs). Although INNs are not new, they have, so\nfar, received little attention in literature. While classical neural networks\nattempt to solve the ambiguous inverse problem directly, INNs are able to learn\nit jointly with the well-defined forward process, using additional latent\noutput variables to capture the information otherwise lost. Given a specific\nmeasurement and sampled latent variables, the inverse pass of the INN provides\na full distribution over parameter space. We verify experimentally, on\nartificial data and real-world problems from astrophysics and medicine, that\nINNs are a powerful analysis tool to find multi-modalities in parameter space,\nto uncover parameter correlations, and to identify unrecoverable parameters.","url_abs":"http://arxiv.org/abs/1808.04730v3","url_pdf":"http://arxiv.org/pdf/1808.04730v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"analyzing-inverse-problems-with-invertible","repo_url":"https://github.com/VLL-HD/analyzing_inverse_problems","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"analyzing-inverse-problems-with-invertible","repo_url":"https://github.com/jaekookang/invertible_neural_networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1808.04730","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}