activity
20182023
most citedPlex: Towards Reliability using Pretrained Large Model Extensions

38 citations · 98 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2023★ 9 cited

A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models

James Urquhart Allingham, Jie Ren, Michael W Dusenberry +5

Contrastively trained text-image models have the remarkable ability to perform zero-shot classification, that is, classifying previously unseen images into categories that the mode…

cs.LG2022★ 38 cited

Plex: Towards Reliability using Pretrained Large Model Extensions

Dustin Tran, Jeremiah Liu, Michael W. Dusenberry +23

A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures. P…

cs.LG2021

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

Zachary Nado, Neil Band, Mark Collier +23

High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ab…

cs.LG2020

Combining Ensembles and Data Augmentation can Harm your Calibration

Yeming Wen, Ghassen Jerfel, Rafael Muller +4

Ensemble methods which average over multiple neural network predictions are a simple approach to improve a model's calibration and robustness. Similarly, data augmentation techniqu…

cs.LG2020★ 33 cited

Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors

Michael W. Dusenberry, Ghassen Jerfel, Yeming Wen +5

Bayesian neural networks (BNNs) demonstrate promising success in improving the robustness and uncertainty quantification of modern deep learning. However, they generally struggle w…

cs.LG2019

Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer

Edward Choi, Zhen Xu, Yujia Li +4

Effective modeling of electronic health records (EHR) is rapidly becoming an important topic in both academia and industry. A recent study showed that using the graphical structure…