no code implementations • NeurIPS 2021 • Jessica Finocchiaro, Rafael Frongillo, Bo Waggoner
The convex consistency dimension of a supervised learning task is the lowest prediction dimension $d$ such that there exists a convex surrogate $L : \mathbb{R}^d \times \mathcal Y \to \mathbb R$ that is consistent for the given task.
no code implementations • NeurIPS 2018 • Jessica Finocchiaro, Rafael Frongillo
A property or statistic of a distribution is said to be elicitable if it can be expressed as the minimizer of some loss function in expectation.
no code implementations • 9 Oct 2016 • Jessica Finocchiaro, Aisha Urooj Khan, Ali Borji
We used both traditional computer vision approaches and deep learning in order to determine the visual cues that results in best height estimation.