English

Yau's Affine Normal Descent: Algorithmic Framework and Convergence Analysis

Optimization and Control 2026-04-06 v2 Machine Learning Numerical Analysis Differential Geometry Numerical Analysis

Abstract

We propose Yau's Affine Normal Descent (YAND), a geometric framework for smooth unconstrained optimization in which search directions are defined by the equi-affine normal of level-set hypersurfaces. The resulting directions are invariant under volume-preserving affine transformations and intrinsically adapt to anisotropic curvature. Using the analytic representation of the affine normal from affine differential geometry, we establish its equivalence with the classical slice-centroid construction under convexity. For strictly convex quadratic objectives, affine-normal directions are collinear with Newton directions, implying one-step convergence under exact line search. For general smooth (possibly nonconvex) objectives, we characterize precisely when affine-normal directions yield strict descent and develop a line-search-based YAND. We establish global convergence under standard smoothness assumptions, linear convergence under strong convexity and Polyak-Lojasiewicz conditions, and quadratic local convergence near nondegenerate minimizers. We further show that affine-normal directions are robust under affine scalings, remaining insensitive to arbitrarily ill-conditioned transformations. Numerical experiments illustrate the geometric behavior of the method and its robustness under strong anisotropic scaling.

Keywords

Cite

@article{arxiv.2603.28448,
  title  = {Yau's Affine Normal Descent: Algorithmic Framework and Convergence Analysis},
  author = {Yi-Shuai Niu and Artan Sheshmani and Shing-Tung Yau},
  journal= {arXiv preprint arXiv:2603.28448},
  year   = {2026}
}

Comments

56 pages, 26 figures

R2 v1 2026-07-01T11:44:08.809Z