378 citations · 1.2k across the 40 of their papers we have counts for
43 papers
Spectral Universality of Regularized Linear Regression with Nearly Deterministic Sensing Matrices
Rishabh Dudeja, Subhabrata Sen, Yue M. Lu
It has been observed that the performances of many high-dimensional estimation problems are universal with respect to underlying sensing (or design) matrices. Specifically, matrice…
Sharp Asymptotics of Kernel Ridge Regression Beyond the Linear Regime
Hong Hu, Yue M. Lu
The generalization performance of kernel ridge regression (KRR) exhibits a multi-phased pattern that crucially depends on the scaling relationship between the sample size and t…
An Equivalence Principle for the Spectrum of Random Inner-Product Kernel Matrices with Polynomial Scalings
Yue M. Lu, Horng-Tzer Yau
We investigate random matrices whose entries are obtained by applying a nonlinear kernel function to pairwise inner products between independent data vectors, drawn uniformly f…
Universality of Approximate Message Passing with Semi-Random Matrices
Rishabh Dudeja, Yue M. Lu, Subhabrata Sen
Approximate Message Passing (AMP) is a class of iterative algorithms that have found applications in many problems in high-dimensional statistics and machine learning. In its gener…
Analysis of Random Sequential Message Passing Algorithms for Approximate Inference
Burak Çakmak, Yue M. Lu, Manfred Opper
We analyze the dynamics of a random sequential message passing algorithm for approximate inference with large Gaussian latent variable models in a student-teacher scenario. To mode…
On the Inherent Regularization Effects of Noise Injection During Training
Oussama Dhifallah, Yue M. Lu
Randomly perturbing networks during the training process is a commonly used approach to improving generalization performance. In this paper, we present a theoretical study of one p…