5 papers
Gradient descent inference in empirical risk minimization
Qiyang Han, Xiaocong Xu
Gradient descent is one of the most widely used iterative algorithms in modern statistical learning. However, its precise algorithmic dynamics in high-dimensional settings remain o…
Long-time dynamics and universality of nonconvex gradient descent
Qiyang Han
This paper develops a general approach to characterize the long-time trajectory behavior of nonconvex gradient descent in generalized single-index models in the large aspect ratio…
A leave-one-out approach to approximate message passing
Zhigang Bao, Qiyang Han, Xiaocong Xu
Approximate message passing (AMP) has emerged both as a popular class of iterative algorithms and as a powerful analytic tool in a wide range of statistical estimation problems and…
Entrywise dynamics and universality of general first order methods
Qiyang Han
General first order methods (GFOMs), including various gradient descent and AMP algorithms, constitute a broad class of iterative algorithms in modern statistical learning problems…
Precise gradient descent training dynamics for finite-width multi-layer neural networks
Qiyang Han, Masaaki Imaizumi
In this paper, we provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks under the canonical single-index re…