A Mathematical Framework for Computability Aspects of Algorithmic Transparency

Holger Boche, Adalbert Fono, Gitta Kutyniok

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

The lack of trustworthiness is a major downside of deep learning. To mitigate the associated risks clear obligations of deep learning models have been proposed via regulatory guidelines. Therefore, a crucial question is to what extent trustworthy deep learning can be realized. Establishing trust-worthiness requires that the factors influencing an algorithmic computation can be retraced, i.e., the algorithmic implementation is transparent. Motivated by the observation that the current evolution of deep learning models necessitates a change in computing technology, we derive a mathematical framework that enables us to analyze whether a transparent implementation in a given computing model is feasible. We exemplarily apply our trustworthiness framework to analyze deep learning approaches for inverse problems in digital and analog computing models represented by Turing and Blum-Shub-Smale Machines, respectively. Based on previous results, we find that Blum-Shub-Smale Machines have the potential to establish trustworthy solvers for inverse problems under fairly general conditions, whereas, Turing machines cannot guarantee trustworthiness to the same degree. For a longer version of this paper with more details and proofs, we refer to [1].

Original languageEnglish
Title of host publication2024 IEEE International Symposium on Information Theory, ISIT 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3089-3094
Number of pages6
ISBN (Electronic)9798350382846
DOIs
StatePublished - 2024
Event2024 IEEE International Symposium on Information Theory, ISIT 2024 - Athens, Greece
Duration: 7 Jul 202412 Jul 2024

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
ISSN (Print)2157-8095

Conference

Conference2024 IEEE International Symposium on Information Theory, ISIT 2024
Country/TerritoryGreece
CityAthens
Period7/07/2412/07/24

Fingerprint

Dive into the research topics of 'A Mathematical Framework for Computability Aspects of Algorithmic Transparency'. Together they form a unique fingerprint.

Cite this