36 citations · 85 across the 23 of their papers we have counts for
24 papers
The distribution of Ridgeless least squares interpolators
Qiyang Han, Xiaocong Xu
The Ridgeless minimum -norm interpolator in overparametrized linear regression has attracted considerable attention in recent years in both machine learning and statistics…
Gaussian random projections of convex cones: approximate kinematic formulae and applications
Qiyang Han, Huachen Ren
Understanding the stochastic behavior of random projections of geometric sets constitutes a fundamental problem in high dimension probability that finds wide applications in divers…
Exact bounds for some quadratic empirical processes with applications
Qiyang Han
Let be i.i.d. isotropic random vectors in , and be a compact set. A classical line of empirical process theory characterizes…
Universality of regularized regression estimators in high dimensions
Qiyang Han, Yandi Shen
The Convex Gaussian Min-Max Theorem (CGMT) has emerged as a prominent theoretical tool for analyzing the precise stochastic behavior of various statistical estimators in the so-cal…
Noisy linear inverse problems under convex constraints: Exact risk asymptotics in high dimensions
Qiyang Han
In the standard Gaussian linear measurement model with a fixed noise level , we consider the problem of estimating the unknown signal under a…
Nonparametric, tuning-free estimation of S-shaped functions
Oliver Y. Feng, Yining Chen, Qiyang Han +2
We consider the nonparametric estimation of an S-shaped regression function. The least squares estimator provides a very natural, tuning-free approach, but results in a non-convex…