cs.LGFeb 3, 2026

A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems

Authors: Ronald Katende

Organizations: Department of Mathematics Kabale University Kikungiri Hill, Katuna Road, 317, Kabale, Uganda

Abstract

Modern learning systems often interpolate training data while still generalizing well, yet it remains unclear when algorithmic stability explains this behavior. We model training as a function-space trajectory and measure sensitivity to single-sample perturbations along this trajectory. We propose a contractive propagation condition and a stability certificate obtained by unrolling the resulting recursion. A small certificate implies stability-based generalization, while we also prove that there exist interpolating regimes with small risk where such contractive sensitivity cannot hold, showing that stability is not a universal explanation. Experiments confirm that certificate growth predicts generalization differences across optimizers, step sizes, and dataset perturbations. The framework therefore identifies regimes where stability explains generalization and where alternative mechanisms must account for success.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Generalization as a robust performance property of learning-enabled dynamical systems

    Aug 31, 2026Filippo FabianiData-Driven ControlGeneralization Bounds

  2. Grokking through the Lens of Minimum-Norm Interpolation

    Sep 29, 2026Gil Kur, Ileana Rugina, Clémentine Carla Juliette Dominé +1Statistical Learning TheoryImplicit Regularization

  3. A Learning Stability Profile for Finite-Dimensional Learning Dynamics

    Dec 24, 2025Ronald KatendeNeural Network StabilityLyapunov Stability