22 citations · 54 across the 5 of their papers we have counts for
6 papers
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…
Phase Transitions in Transfer Learning for High-Dimensional Perceptrons
Oussama Dhifallah, Yue M. Lu
Transfer learning seeks to improve the generalization performance of a target task by exploiting the knowledge learned from a related source task. Central questions include decidin…
A Precise Performance Analysis of Learning with Random Features
Oussama Dhifallah, Yue M. Lu
We study the problem of learning an unknown function using random feature models. Our main contribution is an exact asymptotic analysis of such learning problems with Gaussian data…
Phase Retrieval via Polytope Optimization: Geometry, Phase Transitions, and New Algorithms
Oussama Dhifallah, Christos Thrampoulidis, Yue M. Lu
We study algorithms for solving quadratic systems of equations based on optimization methods over polytopes. Our work is inspired by a recently proposed convex formulation of the p…
Phase Retrieval via Linear Programming: Fundamental Limits and Algorithmic Improvements
Oussama Dhifallah, Christos Thrampoulidis, Yue M. Lu
A recently proposed convex formulation of the phase retrieval problem estimates the unknown signal by solving a simple linear program. This new scheme, known as PhaseMax, is comput…
Fundamental Limits of PhaseMax for Phase Retrieval: A Replica Analysis
Oussama Dhifallah, Yue M. Lu
We consider a recently proposed convex formulation, known as the PhaseMax method, for solving the phase retrieval problem. Using the replica method from statistical mechanics, we a…