Finiteness and complexity in the time of AI

MathAI 2025 Conference Submission18 Authors

31 Jan 2025 (modified: 25 Mar 2025)MathAI 2025 Conference SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: finite, complexity of objects, complexity of computation, big data, machine learning
TL;DR: finite can be different in the physical world, as well as in AI-world
Abstract: In the last period of his activity, A. N. Kolmogorov paid considerable attention to mathematical concepts and problems related to digital technologies. For him, this was due to the transition from continuous to discrete and finite, for which continuous can be a good approximation. Kolmogorov and his students have developed a number of fundamental concepts and results related to computational complexity and the complexity of finite objects. The talk will talk about the current development of Kolmogorov's approaches to the complexity of finite objects and the gradations of finitness and complexity associated with big data and machine learning.
Submission Number: 18
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview