Riemannian Adaptive Regularized Newton Methods with Hölder Continuous Hessians (2309.04052v3)

Abstract: This paper presents strong worst-case iteration and operation complexity guarantees for Riemannian adaptive regularized Newton methods, a unified framework encompassing both Riemannian adaptive regularization (RAR) methods and Riemannian trust region (RTR) methods. We comprehensively characterize the sources of approximation in second-order manifold optimization methods: the objective function's smoothness, retraction's smoothness, and subproblem solver's inexactness. Specifically, for a function with a $\mu$-H\"older continuous Hessian, when equipped with a retraction featuring a $\nu$-H\"older continuous differential and a $\theta$-inexact subproblem solver, both RTR and RAR with $2+\alpha$ regularization (where $\alpha=\min{\mu,\nu,\theta}$) locate an $(\epsilon,\epsilon^{\alpha/(1+\alpha)})$-approximate second-order stationary point within at most $O(\epsilon^{-(2+\alpha)/(1+\alpha)})$ iterations and at most $\tilde{O}(\epsilon^{-(4+3\alpha)/(2(1+\alpha))})$ Hessian-vector products. These complexity results are novel and sharp, and reduce to an iteration complexity of $O(\epsilon^{-3/2})$ and an operation complexity of $\tilde{O}(\epsilon^{-7/4})$ when $\alpha=1$.