Score: 0

Dual Riemannian Newton Method on Statistical Manifolds

Published: November 14, 2025 | arXiv ID: 2511.11318v1

By: Derun Zhou, Keisuke Yano, Mahito Sugiyama

Potential Business Impact:

Speeds up computer learning by using geometry.

Business Areas:
A/B Testing Data and Analytics

In probabilistic modeling, parameter estimation is commonly formulated as a minimization problem on a parameter manifold. Optimization in such spaces requires geometry-aware methods that respect the underlying information structure. While the natural gradient leverages the Fisher information metric as a form of Riemannian gradient descent, it remains a first-order method and often exhibits slow convergence near optimal solutions. Existing second-order manifold algorithms typically rely on the Levi-Civita connection, thus overlooking the dual-connection structure that is central to information geometry. We propose the dual Riemannian Newton method, a Newton-type optimization algorithm on manifolds endowed with a metric and a pair of dual affine connections. The dual Riemannian Newton method explicates how duality shapes second-order updates: when the retraction (a local surrogate of the exponential map) is defined by one connection, the associated Newton equation is posed with its dual. We establish local quadratic convergence and validate the theory with experiments on representative statistical models. Thus, the dual Riemannian Newton method thus delivers second-order efficiency while remaining compatible with the dual structures that underlie modern information-geometric learning and inference.

Page Count
40 pages

Category
Statistics:
Computation