paper-with-me

홈 › Papers

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

2026-02-03 · Ronald Katende arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.03514

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Price of Robustness: Stable Classifiers Need Overparameterization

2026-03-03 · Jonas von Berg, Adalbert Fono, Massimiliano Datres, Sohir Maskey 외 arxiv

The relationship between overparameterization, stability, and generalization remains incompletely understood in the setting of discontinuous classifiers. We address this gap by establishing a generalization bound for fin…

Spectral Koopman Method for Identifying Stability Boundary

2023-12-11 · Bhagyashree Umathe, Umesh Vaidya

The paper is about characterizing the stability boundary of an autonomous dynamical system using the Koopman spectrum. For a dynamical system with an asymptotically stable equilibrium point, the domain of attraction cons…

Data Interpolating Prediction: Alternative Interpretation of Mixup

2019-06-20 · ICLR Workshop LLD 2019 · Takuya Shimada, Shoichiro Yamaguchi, Kohei Hayashi, Sosuke Kobayashi

Data augmentation by mixing samples, such as Mixup, has widely been used typically for classification tasks. However, this strategy is not always effective due to the gap between augmented samples for training and origin…

Data AugmentationGeneral ClassificationPrediction

Interpolating Classifiers Make Few Mistakes

2021-01-28 · Tengyuan Liang, Benjamin Recht

This paper provides elementary analyses of the regret and generalization of minimum-norm interpolating classifiers (MNIC). The MNIC is the function of smallest Reproducing Kernel Hilbert Space norm that perfectly interpo…

chebgreen: Learning and Interpolating Continuous Empirical Green's Functions from Data

2025-01-30 · Harshwardhan Praveen, Jacob Brown, Christopher Earls

In this work, we present a mesh-independent, data-driven library, chebgreen, to mathematically model one-dimensional systems, possessing an associated control parameter, and whose governing partial differential equation …