cond-mat.stat-mech, cs.IT, cs.LG, math.IT, math.ST, stat.ML, stat.TH

Information-Geometric Decomposition of Generalization Error in Unsupervised Learning

arXiv:2604.12340v1 Announce Type: new
Abstract: We decompose the Kullback–Leibler generalization error (GE) — the expected KL divergence from the data distribution to the trained model — of unsupervised learning into three non-negative components: …