# Robustness of Epinets against Distributional Shifts Source: [Robustness of Epinets against Distributional Shifts]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:15:31.627Z Authors: Xiuyuan Lu, Ian Osband, Seyed Mohammad Asghari, Sven Gowal, Vikranth Dwaracherla, Zheng Wen, Benjamin Van Roy Published: 2022-07-01T01:07:11.000Z ## Abstract Recent work introduced the epinet as a new approach to uncertainty modeling in deep learning. An epinet is a small neural network added to traditional neural networks, which, together, can produce predictive distributions. In particular, using an epinet can greatly improve the quality of joint predictions across multiple inputs, a measure of how well a neural network knows what it does not know. In this paper, we examine whether epinets can offer similar advantages under distributional shifts. We find that, across ImageNet-A/O/C, epinets generally improve robustness metrics. Moreover, these improvements are more significant than those afforded by even very large ensembles at orders of magnitude lower computational costs. However, these improvements are relatively small compared to the outstanding issues in distributionally-robust deep learning. Epinets may be a useful tool in the toolbox, but they are far from the complete solution. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()