AI RESEARCH
Bridging Functional and Representational Similarity via Usable Information
arXiv CS.LG
•
ArXi:2601.21568v2 Announce Type: replace We present a unified framework for quantifying the similarity between representations through the lens of \textit{usable} information, offering a rigorous theoretical and empirical synthesis across three key dimensions. First, addressing functional similarity, we establish a formal link between stitching performance and conditional mutual information. We further reveal that stitching is inherently asymmetric, nstrating that robust functional comparison necessitates a bidirectional analysis rather than a unidirectional mapping.