617 citations · 679 across the 4 of their papers we have counts for
5 papers
Adaptive Gradient Methods at the Edge of Stability
Jeremy M. Cohen, Behrooz Ghorbani, Shankar Krishnan +8
Very little is known about the training dynamics of adaptive gradient methods like Adam in deep learning. In this paper, we shed light on the behavior of these algorithms in the fu…
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
Jeremy M. Cohen, Simran Kaur, Yuanzhi Li +2
We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the…
Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?
Simran Kaur, Jeremy Cohen, Zachary C. Lipton
For a standard convolutional neural network, optimizing over the input pixels to maximize the score of some target class will generally produce a grainy-looking version of the orig…
Certified Adversarial Robustness via Randomized Smoothing
Jeremy M Cohen, Elan Rosenfeld, J. Zico Kolter
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the norm.…
Phenomenological forecasting of disease incidence using heteroskedastic Gaussian processes: a dengue case study
Leah R. Johnson, Robert B. Gramacy, Jeremy Cohen +6
In 2015 the US federal government sponsored a dengue forecasting competition using historical case data from Iquitos, Peru and San Juan, Puerto Rico. Competitors were evaluated on…