Publication and Preprints:
- “Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms.”
Yuchen Li, Laura Balzano, Deanna Needell, and Hanbaek Lyu
To appear in International Conference on Machine Learning (ICML 2024) [Paper] - “Block Majorization-minimization with Diminishing Radius for Constrained Nonconvex Optimization.”
Hanbaek Lyu and Yuchen Li
Submitted to SIAM Journal on Optimization (SIOPT) [Preprint, Github] (2023) - “Convergence and Complexity of Block Majorization-minimization for Constrained Block-Riemannian Optimization.”
Yuchen Li, Laura Balzano, Deanna Needell, and Hanbaek Lyu
Submitted to Journal of Machine Learning Research (JMLR) [Preprint] (2023) - “An Efficient Continuous Data Assimilation Algorithm for the Sabra Shell Model of Turbulence.”
Nan Chen, Yuchen Li, and Evelyn Lunasin
Chaos: An Interdisciplinary Journal of Nonlinear Science, Vol.31, Issue 10, 2021. [Journal, Preprint]
Talks:
- “Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms”, IFDS idea forum, Institute for Foundations of Data Science, April 1st 2024
- “Block Majorization-minimization on Riemannian manifolds”, IFDS annual meeting, Institute for Foundations of Data Science, August 2nd 2023. [Poster]
- “Convergence and Complexity of Block Majorization-minimization on Riemannian manifolds”, IFDS idea forum, Institute for Foundations of Data Science, April 10th 2023. [Slides]
- “An Efficient Continuous in Time Data Assimilation Algorithm for Sabra Shell Model of Turbulence”, SIAM Conference on Applications of Dynamical Systems (SIAM DS21), May 23rd-27th 2021. [Slides]