2024/03/26 by Adam Wang, Wang, Adam
Computer Science · #Computability, Logic, AI Algorithms #FOS: Computer and information sciences #Information Theory (cs.IT)
paper · pdf · doi:10.48550/arxiv.2404.02167
openalex publication_date 2024/03/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The following note proves that conditional entropy of a sequence is almost time-reversal invariant, specifically they only differ by a small constant factor dependent only upon the forward and backward models that the entropies are being calculated with respect to. This gives rise to a numerical value that quantifies learnability, as well as a methodology to control for distributional shift between datasets. Rough guidelines are given for practitioners.