Publications

LancBiO: dynamic Lanczos-aided bilevel optimization via Krylov subspace. The 13th International Conference on Learning Representations (ICLR 2025), (2025), accepted.

Code Preprint

Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity. The 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025), (2025), accepted.

Preprint

Riemannian optimization for Holevo capacity. arXiv:2501.11576, (2025).

Code Preprint

Low-rank optimization on Tucker tensor varieties. Mathematical Programming, (2024), accepted.

DOI Code Preprint Slides

Infeasible deterministic, stochastic, and variance-reduction algorithms for optimization under orthogonality constraints. Journal of Machine Learning Research, 25(389) (2024), 1–38.

DOI Code Preprint Slides

Desingularization of bounded-rank tensor sets. arXiv:2411.14093, (2024).

Code Preprint

Symplectic Stiefel manifold: tractable metrics, second-order geometry and Newton's methods. arXiv:2406.14299, (2024).

Preprint

Optimization without retraction on the random generalized Stiefel manifold. Proceedings of the 41st International Conference on Machine Learning (ICML 2024), PMLR 235 (2024), 49226–49248.

DOI Code Slides

Riemannian preconditioned algorithms for tensor completion via tensor ring decomposition. Computational Optimization and Applications, 88 (2024), 443–468.

DOI Code Preprint

Optimization on the symplectic Stiefel manifold: SR decomposition-based retraction and applications. Linear Algebra and Its Applications, 682 (2024), 50–85.

DOI Code Preprint

Alternating minimization algorithms for graph regularized tensor completion. arXiv:2008.12876, (2023).

Code Preprint

Optimization on product manifolds under a preconditioned metric. arXiv:2306.08873, (2023).

Code Preprint Slides

Optimization flows landing on the Stiefel manifold. 25th IFAC Symposium on Mathematical Theory of Networks and Systems (MTNS 2022), IFAC-PapersOnLine, 55-30 (2022), 25–30.

DOI Preprint Slides

On the analysis of optimization with fixed-rank matrices: a quotient geometric view. arXiv:2203.06765, (2022).

Preprint

An orthogonalization-free parallelizable framework for all-electron calculations in density functional theory. SIAM Journal on Scientific Computing, 44-3 (2022), B723–B745.

DOI Preprint

New Riemannian preconditioned algorithms for tensor completion via polyadic decomposition. SIAM Journal on Matrix Analysis and Applications, 43-2 (2022), 840–866.

DOI Code Preprint

A Riemannian rank-adaptive method for low-rank matrix completion. Computational Optimization and Applications, 81 (2022), 67–90.

DOI Code Preprint

Computing symplectic eigenpairs of symmetric positive-definite matrices via trace minimization and Riemannian optimization. SIAM Journal on Matrix Analysis and Applications, 42-4 (2021), 1732–1757.

DOI Code Preprint

Geometry of the symplectic Stiefel manifold endowed with the Euclidean metric. Geometric Science of Information: 5th International Conference (GSI 2021), Lecture Notes in Computer Science, 12829 (2021), 789–796.

DOI Code Preprint

Riemannian optimization on the symplectic Stiefel manifold. SIAM Journal on Optimization, 31-2 (2021), 1546–1575.

DOI Code Preprint

Multipliers correction methods for optimization problems over the Stiefel manifold. CSIAM Transactions on Applied Mathematics, 2-3 (2021), 508–531.

DOI Preprint

Parallelizable algorithms for optimization problems with orthogonality constraints. SIAM Journal on Scientific Computing, 41-3 (2019), A1949–A1983.

DOI Code Preprint

A new first-order algorithmic framework for optimization problems with orthogonality constraints. SIAM Journal on Optimization, 28-1 (2018), 302–332.

DOI Code Preprint

First-order algorithms for optimization problems with orthogonality constraints. OR Transactions (in Chinese), 21-4 (2017), 57–68.

DOI

On the Łojasiewicz exponent of the quadratic sphere constrained optimization problem. arXiv:1611.08781, (2016).

Preprint