An Adaptive Smoothing Algorithm for Non-Lipschitz Optimization on Manifolds with Complexity Guarantees
Year: 2026
Type: preprint
Abstract: We study a class of optimization problems on Riemannian manifolds, where the objective function consists of a smooth term and quasi-norm type penalties with exponent $p \in (0, 1]$. The essential difficulty lies in the fact that the objective function may not be locally Lipschitz continuous, which places this type of problems beyond the reach of existing Riemannian techniques. To overcome this obstacle, this paper constructs a general smoothing framework and establishes fundamental properties for developing efficient algorithms. In particular, we propose a smoothing Riemannian gradient algorithm equipped with a smoothing-aware AdaGrad-type stepsize rule. Its global convergence is demonstrated together with an iteration complexity of $O (ε^{p - 4})$, which includes the best available iteration complexity of $O (ε^{- 3})$ for Lipschitz problems with $p = 1$ as a special case. To the best of our knowledge, this is the first complexity result for non-Lipschitz optimization on Riemannian manifolds. Preliminary numerical experiments corroborate the practical efficiency of the proposed approach in real-world applications arsing from machine learning and data science.
Source: arXiv (Cornell University)
Authors: Wang, Lei, Chen, Xiaojun
Institution: Hong Kong Polytechnic University
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Hong Kong Polytechnic University
OpenAlex ID: W7155056124
Cites:
Cited by:
Related to: