David M. Rosen

collaborators

2 papers

cs.LG2026

$(DNN)^{2}$ : Doubly Non-Negative Relaxations for Deep Neural Networks

Hanna Jiamei Zhang, Alan Papalia, Michael Everett +1

Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-conservative safety guarantee…

cs.RO2024

An Overview of the Burer-Monteiro Method for Certifiable Robot Perception

Alan Papalia, Yulun Tian, David M. Rosen +2

This paper presents an overview of the Burer-Monteiro method (BM), a technique that has been applied to solve robot perception problems to certifiable optimality in real-time. BM i…

(DNN)2: Doubly Non-Negative Relaxations for Deep Neural Networks

An Overview of the Burer-Monteiro Method for Certifiable Robot Perception

$(DNN)^{2}$ : Doubly Non-Negative Relaxations for Deep Neural Networks