[2603.23220] General Machine Learning: Theory for Learning Under Variable Regimes

Computer Science > Machine Learning arXiv:2603.23220 (cs) [Submitted on 24 Mar 2026] Title:General Machine Learning: Theory for Learning Under Variable Regimes Authors:Aomar Osmani View a PDF of the paper titled General Machine Learning: Theory for Learning Under Variable Regimes, by Aomar Osmani View PDF HTML (experimental) Abstract:We study learning under regime variation, where the learner, its memory state, and the evaluative conditions may evolve over time. This paper is a foundational and structural contribution: its goal is to define the core learning-theoretic objects required for such settings and to establish their first theorem-supporting consequences. The paper develops a regime-varying framework centered on admissible transport, protected-core preservation, and evaluator-aware learning evolution. It records the immediate closure consequences of admissibility, develops a structural obstruction argument for faithful fixed-ontology reduction in genuinely multi-regime settings, and introduces a protected-stability template together with explicit numerical and symbolic witnesses on controlled subclasses, including convex and deductive settings. It also establishes theorem-layer results on evaluator factorization, morphisms, composition, and partial kernel-level alignment across semantically commensurable layers. A worked two-regime example makes the admissibility certificate, protected evaluative core, and regime-variation cost explicit on a controlled subclass. Th...