Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Simran Kaur

Simran Kaur

Disentangling the Mechanisms Behind Implicit Regularization in SGD

Nov 29, 2022
Zachary Novack, Simran Kaur, Tanya Marwah, Saurabh Garg, Zachary C. Lipton

Figure 1 for Disentangling the Mechanisms Behind Implicit Regularization in SGD

Figure 2 for Disentangling the Mechanisms Behind Implicit Regularization in SGD

Figure 3 for Disentangling the Mechanisms Behind Implicit Regularization in SGD

Figure 4 for Disentangling the Mechanisms Behind Implicit Regularization in SGD

* Accepted as Spotlight at the NeurIPS 2022 Workshop for Higher Order Optimization in Machine Learning

Access Paper or Ask Questions

Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

Feb 26, 2021
Jeremy M. Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar

Figure 1 for Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

Figure 2 for Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

Figure 3 for Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

Figure 4 for Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

* To appear in ICLR 2021. 72 pages, 107 figures

Access Paper or Ask Questions

Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

Oct 23, 2019
Simran Kaur, Jeremy Cohen, Zachary C. Lipton

Figure 1 for Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

Figure 2 for Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

Figure 3 for Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

Figure 4 for Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

* To appear in the "Science Meets Engineering of Deep Learning" Workshop at NeurIPS 2019

Access Paper or Ask Questions