no code implementations • 18 Dec 2021 • Alex Devonport, Forest Yang, Laurent El Ghaoui, Murat Arcak
In addition to applying classical Vapnik-Chervonenkis (VC) dimension bound arguments, we apply the PAC-Bayes theorem by leveraging a formal connection between kernelized empirical inverse Christoffel functions and Gaussian process regression models.
no code implementations • 28 Apr 2021 • Alex Devonport, Forest Yang, Laurent El Ghaoui, Murat Arcak
We present an algorithm for data-driven reachability analysis that estimates finite-horizon forward reachable sets for general nonlinear systems using level sets of a certain class of polynomials known as Christoffel functions.
no code implementations • NeurIPS 2020 • Forest Yang, Mouhamadou Cisse, Oluwasanmi O. Koyejo
In algorithmically fair prediction problems, a standard goal is to ensure the equality of fairness metrics across multiple overlapping groups simultaneously.
no code implementations • 24 Jun 2020 • Forest Yang, Moustapha Cisse, Sanmi Koyejo
In algorithmically fair prediction problems, a standard goal is to ensure the equality of fairness metrics across multiple overlapping groups simultaneously.
no code implementations • ICML 2020 • Forest Yang, Sanmi Koyejo
Our analysis continues by showing previously proposed hinge-like top-$k$ surrogate losses are not top-$k$ calibrated and suggests no convex hinge loss is top-$k$ calibrated.
no code implementations • 18 Jun 2018 • Armin Askari, Forest Yang, Laurent El Ghaoui
Outlier detection methods have become increasingly relevant in recent years due to increased security concerns and because of its vast application to different fields.