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

Ha Manh Bui, Anqi Liu
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:2998-3006, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-manh-bui24a, title = {Density-Regression: Efficient and Distance-aware Deep Regressor for Uncertainty Estimation under Distribution Shifts}, author = {Manh Bui, Ha and Liu, Anqi}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {2998--3006}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/manh-bui24a/manh-bui24a.pdf}, url = {https://proceedings.mlr.press/v238/manh-bui24a.html}, 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.} }
Endnote
%0 Conference Paper %T Density-Regression: Efficient and Distance-aware Deep Regressor for Uncertainty Estimation under Distribution Shifts %A Ha Manh Bui %A Anqi Liu %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-manh-bui24a %I PMLR %P 2998--3006 %U https://proceedings.mlr.press/v238/manh-bui24a.html %V 238 %X 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.
APA
Manh Bui, H. & Liu, A.. (2024). Density-Regression: Efficient and Distance-aware Deep Regressor for Uncertainty Estimation under Distribution Shifts. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:2998-3006 Available from https://proceedings.mlr.press/v238/manh-bui24a.html.

Related Material