Скачать с ютуб Deep Ensembles Work, But Are They Necessary? | AI Talks в хорошем качестве

Deep Ensembles Work, But Are They Necessary? | AI Talks

Ensembling neural networks is an effective way to increase accuracy, and can often match the performance of individual larger models. This observation poses a natural question: given the choice between a deep ensemble and a single neural network with similar accuracy, is one preferable over the other? Recent work suggests that deep ensembles may offer distinct benefits beyond predictive power: namely, uncertainty quantification and robustness to dataset shift. In this work, we demonstrate limitations to these purported benefits, and show that a single (but larger) neural network can replicate these qualities. First, we show that ensemble diversity, by any metric, does not meaningfully contribute to an ensemble’s uncertainty quantification on out-of-distribution (OOD) data, but is instead highly correlated with the relative improvement of a single larger model. Second, we show that the OOD performance afforded by ensembles is strongly determined by their in-distribution (InD) performance, and—in this sense—is not indicative of any “effective robustness.” While deep ensembles are a practical way to achieve improvements to predictive power, uncertainty quantification, and robustness, our results show that these improvements can be replicated by a (larger) single model. About Speaker: Kelly Buchanan is a Ph.D. candidate at the Zuckerman Institute in Columbia University advised by Liam Paninski and John Cunningham. Her research focuses on machine learning and computer vision for computational neuroscience and computational neuroethology. Kelly has been part of the Reliable Deep Learning Team at Google Brain and X, the Moonshot Factory. Before attending Columbia University, she got her BS and MS with Honors in Electrical Engineering at the University of Kansas.