No AI summary available for this article.
Why It Matters
Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples. In this paper, we bridge the gap between theory and practical applications. We first show that existing definition of concept shift breaks when the source and target supports mismatch. Leveraging entropic optimal transport, we propose a key notion: $γ^{*}\!$-concept shifts, and derive a general error bound unifying covariate and $γ^{*}\!$-concept shifts, which applies to broad loss functions,...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.11918v1 · Indexed about 3 hours ago