11 papers
Heavy-Ball Method under Randomized Schedules
Chang He, Shuzhong Zhang
We study how predefined randomized parameter schedules accelerate the heavy-ball method on general smooth convex objectives. Our analysis distinguishes two levels of randomization:…
On the Nature of Regularity Assumptions in Bilevel Optimization with Constrained Lower-level Problem
Xiaotian Jiang, Chang He, Mingyi Hong +1
In this paper, we study the regularity assumptions commonly adopted in bilevel optimization with constrained lower-level problems, including the linear independence constraint qual…
Adaptive Single-Loop Methods for Stochastic Minimax Optimization on Riemannian Manifolds
Hongye Wang, Chang He, Bo Jiang
Stochastic minimax optimization on Riemannian manifolds has recently attracted significant attention due to its broad range of applications, such as robust training of neural netwo…
On Approximation Algorithms for Commutative Quaternion Polynomial Optimization
Chang He, Bo Jiang, Hongye Wang +1
Quaternion optimization has attracted significant interest due to its broad applications, including color face recognition, video compression, and signal processing. Despite the gr…
History-Aware Adaptive High-Order Tensor Regularization
Chang He, Bo Jiang, Yuntian Jiang +2
In this paper, we develop a new adaptive regularization method for minimizing a composite function, which is the sum of a th-order () Lipschitz continuous function and…
The Second-Order Tâtonnement: Decentralized Interior-Point Methods for Market Equilibrium
Chuwen Zhang, Chang He, Bo Jiang +1
The tâtonnement process and Smale's process are two classical approaches to compute market equilibrium in exchange economies. While the tâtonnement process can be seen as a first-o…
Federated Learning on Riemannian Manifolds: A Gradient-Free Projection-Based Approach
Hongye Wang, Zhaoye Pan, Chang He +2
Federated learning (FL) has emerged as a powerful paradigm for collaborative model training across distributed clients while preserving data privacy. However, existing FL algorithm…
On Relatively Smooth Optimization over Riemannian Manifolds
Chang He, Jiaxiang Li, Bo Jiang +2
We study optimization over Riemannian embedded submanifolds, where the objective function is relatively smooth in the ambient Euclidean space. Such problems have broad applications…
Non-Stationary Bandit Convex Optimization: An Optimal Algorithm with Two-Point Feedback
Chang He, Bo Jiang, Shuzhong Zhang
This paper studies bandit convex optimization in non-stationary environments with two-point feedback, using dynamic regret as the performance measure. We propose an algorithm based…
Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity
Chang He, Zhaoye Pan, Xiao Wang +1
Optimization problems with access to only zeroth-order information of the objective function on Riemannian manifolds arise in various applications, spanning from statistical learni…
Beyond Nonconvexity: A Universal Trust-Region Method with New Analyses
Yuntian Jiang, Chang He, Chuwen Zhang +3
The trust-region (TR) method is renowned historically for its robustness in nonconvex problems and extraordinary numerical performance, but the study of its performance in convex o…