7 papers
Top Singular Value in Sum-Products of Random Matrices
Kevin Han Huang, Boris Hanin
We study the top singular value for a sum of independent random matrices, each of which is a product of i.i.d. Gaussian matrices. Our main conceptu…
The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression
Kevin Han Huang, Haoyu Ye, Somak Laha +1
Over-parameterized linear regression has been widely studied over the last decade. However, most existing works assume that the covariates are independent and that their covariance…
Data augmented bootstrap: Unifying confidence interval construction by approximate invariance
Kevin Han Huang
We propose the data augmented bootstrap (DAB), a framework for constructing confidence intervals from approximately invariant transformations of the data. As special cases, DAB rec…
Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation
Matthew Esmaili Mallory, Kevin Han Huang, Morgane Austern
Over the last decade, a wave of research has characterized the exact asymptotic risk of many high-dimensional models in the proportional regime. Two foundational results have drive…
Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation
Kevin Han Huang, Ni Zhan, Elif Ertekin +2
Incorporating group symmetries into neural networks has been a cornerstone of success in many AI-for-science applications. Diagonal groups of isometries, which describe the invaria…
Slow rates of approximation of U-statistics and V-statistics by quadratic forms of Gaussians
Kevin Han Huang, Peter Orbanz
We construct examples of degree-two U- and V-statistics of i.i.d.~heavy-tailed random vectors in , whose -th moments exist for , and provide tight…