10 papers
Standard Transformers Achieve the Minimax Rate in Nonparametric Regression with Targets
Yanming Lai, Defeng Sun
The tremendous success of Transformer models in fields such as large language models and computer vision necessitates a rigorous theoretical investigation. To the best of our knowl…
Complexity of normalized stochastic first-order methods with momentum under heavy-tailed noise
Chuan He, Zhaosong Lu, Defeng Sun +1
In this paper, we propose practical normalized stochastic first-order methods with Polyak momentum, multi-extrapolated momentum, and recursive momentum for solving unconstrained op…
The Aubin Property for Generalized Equations over -cone Reducible Sets
Jiaming Ma, Defeng Sun
This paper establishes the equivalence between the Aubin property and strong regularity for generalized equations over -cone reducible sets. This result resolves a long-standi…
Progressive Bound Strengthening via Doubly Nonnegative Cutting Planes for Nonconvex Quadratic Programs
Zheng Qu, Defeng Sun, Jintao Xu
We introduce a cutting-plane framework for nonconvex quadratic programs (QPs) that progressively tightens convex relaxations. Our approach leverages the doubly nonnegative (DNN) re…
Robust Gradient Descent Estimation for Tensor Models under Heavy-Tailed Distributions
Xiaoyu Zhang, Di Wang, Guodong Li +1
Low-rank tensor models are widely used in statistics. However, most existing methods rely heavily on the assumption that data follows a sub-Gaussian distribution. To address the ch…
On the -order Semismoothness of the Metric Projection onto Slices of the Positive Semidefinite Cone
Ruoning Chen, Jiaming Ma, Defeng Sun
The metric projection onto the positive semidefinite (PSD) cone is strongly semismooth, a property that guarantees local quadratic convergence for many powerful algorithms in semid…