924 citations · 5.3k across the 63 of their papers we have counts for
7 papers · 1 filter
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Dan Hendrycks, Norman Mu, Ekin D. Cubuk +3
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated i…
Normalizing Flows for Probabilistic Modeling and Inference
George Papamakarios, Eric Nalisnick, Danilo Jimenez Rezende +2
Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a seri…
Deep Ensembles: A Loss Landscape Perspective
Stanislav Fort, Huiyi Hu, Balaji Lakshminarayanan
Deep ensembles have been empirically shown to be a promising approach for improving accuracy, uncertainty and out-of-distribution robustness of deep learning models. While deep ens…
Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh +1
Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 20…
Likelihood Ratios for Out-of-Distribution Detection
Jie Ren, Peter J. Liu, Emily Fertig +5
Discriminative neural networks offer little or no performance guarantees when deployed on data not generated by the same process as the training distribution. On such out-of-distri…
Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
Yaniv Ovadia, Emily Fertig, Jie Ren +6
Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful…
Hybrid Models with Deep and Invertible Features
Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh +2
We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive pr…