Research / BFI Working PaperApr 06, 2021

Universal Prediction Band via Semi-Definite Programming

We propose a computationally efficient method to construct nonparametric, heteroskedastic prediction bands for uncertainty quantification, with or without any user-specified predictive model. The data-adaptive prediction band is universally applicable with minimal distributional assumptions, with strong non-asymptotic coverage properties, and easy to implement using standard convex programs. Our approach can be viewed as a novel variance interpolation with confidence and further leverages techniques from semi-definite programming and sum-of-squares optimization. Theoretical and numerical performances for the proposed approach for uncertainty quantification are analyzed.

More Research From These Scholars

BFI Working Paper Oct 16, 2020

A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum-L1-Norm Interpolated Classifiers

Tengyuan Liang, Pragya Sur
Topics:  Technology & Innovation
BFI Working Paper Oct 16, 2020

How Well Generative Adversarial Networks Learn Distributions

Tengyuan Liang
Topics:  Technology & Innovation
BFI Working Paper Oct 16, 2020

Mehler’s Formula, Branching Process, and Compositional Kernels of Deep Neural Networks

Tengyuan Liang, Hai Tran-Bach
Topics:  Technology & Innovation