SOURCE-LINKED INTELLIGENCE

Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

We continue the study of relatively smart learning, introduced by Dughmi and Pour (2026), which asks a supervised learner to compete, marginal by marginal, with every distribution-fixed error guarantee soundly certifiable from unlabeled data. They showed that the One-Inclusion Graph (OIG) learner is relatively smart with a quadratic sample-complexity blowup, and that no relatively smart learner can do better, leaving open whether ERM or another natural or tractable learner achieves comparable guarantees. They also left open whether the blowup can be restricted to unlabeled data. Our firs resul

Read original source ↗ Open in workspace

recordType

paper

region

Global