Harmonic Map Regression: Rate-Optimal Nonparametric Estimation on Manifolds with Topological Recovery

2026-04-10

AI Summary

This work addresses the challenge of geometric and topological consistency in nonparametric regression with manifold-valued response variables, where complex topology impedes conventional approaches. The authors propose harmonic map regression, which regularizes the empirical Fréchet risk with Dirichlet energy and leverages variational calculus and the Euler–Lagrange equation to derive piecewise geodesic spline estimators amenable to finite-dimensional optimization. A key contribution is the first theoretical demonstration of topological recovery in manifold regression: the estimator correctly recovers the homotopy class of the true regression curve with probability tending to one. The paper establishes a parallel structural theory to Euclidean smoothing splines, adapted to manifold geometry, and derives pointwise risk convergence rates of \(n^{-2/3}\) and minimax-optimal rates of \(n^{-2s/(2s+1)}\) under Sobolev smoothness of order \(s\). Numerical experiments on \(S^2\), \(\mathbb{H}^2\), \(SO(3)\), \(\mathrm{Sym}^+(2)\), and \(T^2\), along with an application to wind direction data, confirm the method’s efficacy and practicality.

Technology Category

• Machine Learning: Learning with Manifolds
• Search and Optimization: Non-convex Optimization
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

We study harmonic map regression, a nonparametric estimator for manifold-valued responses, that penalizes the empirical Fr\'echet risk by the Dirichlet energy. By connecting penalized regression to the theory of harmonic maps, the estimator acquires a structural theory that parallels the classical Euclidean smoothing spline. The Euler-Lagrange equation characterizes the solution as a piecewise-geodesic spline, an equivalent kernel controls pointwise risk at the rate $n^{-2/3}$, and the infinite-dimensional variational problem reduces exactly to a finite-dimensional optimization. Such newly established connection reveals a topological phenomenon that has no analogue in Euclidean nonparametric regression and, to our knowledge, has not been studied in the manifold regression literature. On manifolds whose regression curves can wrap around in topologically distinct ways, maps in distinct homotopy classes are separated by energy barriers intrinsic to the geometry of the target, and the Dirichlet penalty makes the estimator sensitive to this structure, recovering the correct topological class with probability tending to one, a phase transition we call topological recovery. A curvature-dependent oracle inequality yields the minimax rate $n^{-2s/(2s+1)}$ for Sobolev order $s$, matching the Euclidean constant on non-positively curved targets, while five geometric obstructions show that the full structural theory is unique to the Dirichlet energy ($s=1$). Simulations on $S^2$, $\mathbb{H}^2$, $SO(3)$, $\mathrm{Sym}^+(2)$, and $T^2$ corroborate the theory, and an application to wind-direction data on $S^1$ illustrates practical advantages.

Problem

• manifold-valued regression
• topological recovery
• harmonic maps
• nonparametric estimation
• Dirichlet energy

Innovation

• harmonic map regression
• topological recovery
• Dirichlet energy
• manifold-valued regression
• minimax rate