A Theory of Usable Information under Computational Constraints | OpenReview

A Theory of Usable Information under Computational Constraints Sep 25, 2019 Blind Submission readers: everyone Show Bibtex Abstract: We propose a new framework for reasoning about information in complex systems. Our foundation is based on a variational extension of Shannon’s information theory that takes into account the modeling power and computational constraints of the observer. The resulting predictive V-information encompasses mutual information and other notions of informativeness su

Date: 2020/05/03 00:51

Related Entries

Read more Multilingual Alignment of Contextual Word Representations | OpenReview
0 users, 1 mentions 2020/05/03 00:51
Read more The Curious Case of Neural Text Degeneration | OpenReview
0 users, 1 mentions 2020/05/03 00:51
Read more Finite Depth and Width Corrections to the Neural Tangent Kernel | OpenReview
0 users, 1 mentions 2020/05/03 00:51
Read more [2004.06231] Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuitsopen sea...
0 users, 1 mentions 2020/07/19 00:52
Read more [2002.08563] The continuous categorical: a novel simplex-valued exponential familyopen searchopen na...
0 users, 1 mentions 2020/07/19 02:21