Nonsmooth Riemannian optimization is still a scarcely explored subfield of optimization
theory that concerns the general problem of minimizing (or maximizing) over a domain …

We consider stochastic zeroth-order optimization over Riemannian submanifolds embedded
in Euclidean space, where the task is to solve Riemannian optimization problems with only …

With the rise of machine learning, hyperspectral image (HSI) unmixing problems have been
tackled using learning-based methods. However, physically meaningful unmixing results are …

We study numerical optimization algorithms that use zeroth-order information to minimize
time-varying geodesically convex cost functions on Riemannian manifolds. In the Euclidean …

Riemannian optimization is a principled framework for solving optimization problems where
the desired optimum is constrained to a smooth manifold $\mathcal {M} $. Algorithms …

Stochastic zeroth-order optimization concerns problems where only noisy function
evaluations are available. Such problems arises frequently in many important applications …

[BPT07] RK Beatson, MJD Powell, and AM Tan. Fast evaluation of polyharmonic splines in
three dimensions. IMA Journal of Numerical Analysis, 27 (3): 427–450, July 2007. CODEN …

Riemannian Optimization (RO) is a vibrant and important research area in the field of
optimization theory, which focuses on optimizing real-valued functions over Riemannian …

Optimization on Riemannian manifolds is a topic that draws attention widely in the
optimization community due to its applications in various fields. The problem differs from …