Generalization Bounds with Data-dependent Fractal Dimensions

TL;DR

This paper introduces data-dependent fractal dimensions to provide neural network generalization bounds without Lipschitz assumptions, linking fractal geometry, mutual information, and topological data analysis for improved understanding and computation.

Contribution

It develops a novel data-dependent fractal dimension framework that removes the Lipschitz requirement and connects to topological data analysis for efficient computation.

Findings

Bounds hold without Lipschitz assumptions

Introduces a data-dependent fractal dimension

Links bounds to topological data analysis

Abstract

Providing generalization guarantees for modern neural networks has been a crucial task in statistical learning. Recently, several studies have attempted to analyze the generalization error in such settings by using tools from fractal geometry. While these works have successfully introduced new mathematical tools to apprehend generalization, they heavily rely on a Lipschitz continuity assumption, which in general does not hold for neural networks and might make the bounds vacuous. In this work, we address this issue and prove fractal geometry-based generalization bounds without requiring any Lipschitz assumption. To achieve this goal, we build up on a classical covering argument in learning theory and introduce a data-dependent fractal dimension. Despite introducing a significant amount of technical complications, this new notion lets us control the generalization error (over either fixed or random hypothesis spaces) along with certain mutual information (MI) terms. To provide a clearer interpretation to the newly introduced MI terms, as a next step, we introduce a notion of "geometric stability" and link our bounds to the prior art. Finally, we make a rigorous connection between the proposed data-dependent dimension and topological data analysis tools, which then enables us to compute the dimension in a numerically efficient way. We support our theory with experiments conducted on various settings.