21 citations · 30 across the 9 of their papers we have counts for
3 papers · 1 filter
Benchmarking Neural Network Training Algorithms
George E. Dahl, Frank Schneider, Zachary Nado +22
Training algorithms, broadly construed, are an essential part of every deep learning pipeline. Training algorithm improvements that speed up training across a wide variety of workl…
Efficient CDF Approximations for Normalizing Flows
Chandramouli Shama Sastry, Andreas Lehrmann, Marcus Brubaker +1
Normalizing flows model a complex target distribution in terms of a bijective transform operating on a simple base distribution. As such, they enable tractable computation of a num…
Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
Chandramouli Shama Sastry, Sageev Oore
When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions. Detecting OOD examples is challenging, and the potential risks…