A Generalization of Amari's Bayesian Duality
Abstract
Amari's contributions to information geometry and machine learning are well known. Here, we revisit Amari's work on Bayesian duality which has not received as much attention. We connect Amari's Bayesian duality to a convex duality of Bayes' rule. Using this connection, we present a generalization of Amari's Bayesian duality and discuss its relevance for modern artificial intelligence. --- Source: arXiv:2609.09126v1 - http://arxiv.org/abs/2609.09126v1 PDF: https://arxiv.org/pdf/2609.09126v1 Origi...
Description / Details
Amari's contributions to information geometry and machine learning are well known. Here, we revisit Amari's work on Bayesian duality which has not received as much attention. We connect Amari's Bayesian duality to a convex duality of Bayes' rule. Using this connection, we present a generalization of Amari's Bayesian duality and discuss its relevance for modern artificial intelligence.
Source: arXiv:2609.09126v1 - http://arxiv.org/abs/2609.09126v1 PDF: https://arxiv.org/pdf/2609.09126v1 Original Link: http://arxiv.org/abs/2609.09126v1
Please sign in to join the discussion.
No comments yet. Be the first to share your thoughts!
Sep 9, 2026
Data Science
Statistics
0