activity
20152025
most citedAugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

571 citations · 1.7k across the 29 of their papers we have counts for

collaborators
Showing stat.MLShow all

16 papers · 1 filter

stat.ML2023★ 3 cited

Morse Neural Networks for Uncertainty Quantification

Benoit Dherin, Huiyi Hu, Jie Ren +2

We introduce a new deep generative model useful for uncertainty quantification: the Morse neural network, which generalizes the unnormalized Gaussian densities to have modes of hig…

stat.ML2020

Bayesian Deep Ensembles via the Neural Tangent Kernel

Bobby He, Balaji Lakshminarayanan, Yee Whye Teh

We explore the link between deep ensembles and Gaussian processes (GPs) through the lens of the Neural Tangent Kernel (NTK): a recent development in understanding the training dyna…

stat.ML2019★ 571 cited

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…

stat.ML2019

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…

stat.ML2019

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…

stat.ML2019

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…