Composite modeling reveals dimension reduction linked to data curvature

Geometric Stability and Sample Complexity for Compositional Function Priors

Machine Learning

Summary

This paper studies how understanding the shape of data can help simplify learning tasks. The authors show that if data points lie close to a curved, low-dimensional surface, complex functions can be approximated by smoother functions with fewer variables. They introduce a way to measure how much correcting a simple linear model improves accuracy based on the data's curvature. This helps balance the complexity of learning models with how data is structured, which can improve predictions and reduce errors.

What this means in practice

A theory result. No direct application yet.

Authors

Christopher L. Hammond

Abstract

We study when compositional structure yields dimension reduction in supervised learning. We frame learning as empirical risk minimization with a function-space prior: a regularization functional selects a subset of functions with favorable approximation and metric entropy. The models are compositions $f(x)=g(Ax+Δh(x))$, where $A\in\mathbb{R}^{k\times d}$ is a linear base map, $Δh$ is a nonlinear correction, and $g$ is an outer function; that is, $f$ is an arbitrary smooth function of a $k$-dimensional representation of the input that is linear up to a correction. We prove covering-number bounds showing that the statistical complexity of this class interpolates between an intrinsic regime, parametric in the $kd$ entries of the linear map and nonparametric only in the representation dimension $k$, and an ambient $d$-dimensional nonparametric rate; the interpolation is controlled by the correction size $\varepsilon=\|Δh\|$. We then connect $\varepsilon$ to data geometry. If the data lie in a small tube around a $k$-dimensional manifold and the regression target depends on the input only through its nearest point on that manifold, then locally the target factorizes exactly as $g(Ax+Δh(x))$ with $A$ a tangent chart and a correction whose Sobolev norm scales linearly with curvature at the localization scale. Patching such local models over an atlas gives a finite-sample excess-risk bound for a least-squares estimator over a finite net of local models, whose ambient term vanishes with curvature. For a one-dimensional model problem we also prove a converse: on curved data, every affine compositional predictor faces an error floor unless its correction budget scales with curvature, while the matching curved model class attains the intrinsic rate. The correction size $\varepsilon$ is thus the effective-dimension parameter linking curvature to statistical complexity.