Skip to yearly menu bar Skip to main content


Poster

Density-Regression: Efficient and Distance-aware Deep Regressor for Uncertainty Estimation under Distribution Shifts

Ha Manh Bui · Anqi Liu

MR1 & MR2 - Number 68
[ ] [ Project Page ]
Sat 4 May 6 a.m. PDT — 8:30 a.m. PDT

Abstract:

Morden deep ensembles technique achieves strong uncertainty estimation performance by going through multiple forward passes with different models. This is at the price of a high storage space and a slow speed in the inference (test) time. To address this issue, we propose Density-Regression, a method that leverages the density function in uncertainty estimation and achieves fast inference by a single forward pass. We prove it is distance aware on the feature space, which is a necessary condition for a neural network to produce high-quality uncertainty estimation under distribution shifts. Empirically, we conduct experiments on regression tasks with the cubic toy dataset, benchmark UCI, weather forecast with time series, and depth estimation under real-world shifted applications. We show that Density-Regression has competitive uncertainty estimation performance under distribution shifts with modern deep regressors while using a lower model size and a faster inference speed.

Live content is unavailable. Log in and register to view live content