SOURCE-LINKED INTELLIGENCE

Even Sharper Bounds for Transductive Learning and Its Applications

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

We introduce Sharper Transductive Local Complexity (STLC), a localized complexity method for transductive learning under uniform sampling without replacement. The construction starts from a Bernstein-type concentration inequality for the supremum of the test--train empirical process. Its proof uses the modified log-Sobolev inequality for the swap walk and a two-parameter entropy closure. A peeling argument with a surrogate localization functional then gives excess-risk bounds with the same fixed-point and confidence terms as the classical inductive local Rademacher-complexity bounds, without t

Read original source ↗ Open in workspace

recordType

paper

region

Global