18 citations · 43 across the 4 of their papers we have counts for
5 papers
Datamodels: Predicting Predictions from Training Data
Andrew Ilyas, Sung Min Park, Logan Engstrom +2
We present a conceptual framework, datamodeling, for analyzing the behavior of a model class in terms of the training data. For any fixed "target" example , training set , an…
3DB: A Framework for Debugging Computer Vision Models
Guillaume Leclerc, Hadi Salman, Andrew Ilyas +9
We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation. We demonstrate, through a wide range of use cases, that…
Revisiting Ensembles in an Adversarial Context: Improving Natural Accuracy
Aditya Saligrama, Guillaume Leclerc
A necessary characteristic for the deployment of deep learning models in real world applications is resistance to small adversarial perturbations while maintaining accuracy on non-…
The Two Regimes of Deep Network Training
Guillaume Leclerc, Aleksander Madry
Learning rate schedule has a major impact on the performance of deep learning models. Still, the choice of a schedule is often heuristical. We aim to develop a precise understandin…
Smallify: Learning Network Size while Training
Guillaume Leclerc, Manasi Vartak, Raul Castro Fernandez +2
As neural networks become widely deployed in different applications and on different hardware, it has become increasingly important to optimize inference time and model size along…