Jiaxiang Li

Papers

Total Citations

H-Index

About

Jiaxiang Li is a rising researcher whose work lies at the intersection of optimization, Riemannian geometry, and stochastic methods. His primary research areas include zeroth-order optimization, Riemannian derivative estimation, and non-convex optimization on manifolds. Li's major contribution is the development of novel stochastic zeroth-order Riemannian gradient estimators, which enable optimization over curved geometric spaces using only noisy function evaluations—a critical advance for problems where gradient information is unavailable or expensive. His 2022 paper on this topic has already garnered 20 citations, signaling its foundational impact. Li's work bridges theoretical rigor and practical applicability, offering tools for machine learning, signal processing, and scientific computing where data naturally resides on manifolds. His achievements include pioneering the first principled approach to zeroth-order Riemannian optimization, opening new avenues for derivative-free methods in geometric settings. For students and researchers, Li's research represents a compelling frontier: it tackles fundamental challenges in optimization while providing actionable algorithms for real-world problems, from robotics to medical imaging. His growing citation record underscores the community's recognition of his contributions to this emerging field.