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

Add to Chrome

Add to Firefox

Picture for Saurabh Garg

Saurabh Garg

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

Characterizing Datapoints via Second-Split Forgetting

Oct 26, 2022
Pratyush Maini, Saurabh Garg, Zachary C. Lipton, J. Zico Kolter

Figure 1 for Characterizing Datapoints via Second-Split Forgetting

Figure 2 for Characterizing Datapoints via Second-Split Forgetting

Figure 3 for Characterizing Datapoints via Second-Split Forgetting

Figure 4 for Characterizing Datapoints via Second-Split Forgetting

* Accepted at NeurIPS 2022

Access Paper or Ask Questions

Unsupervised Learning under Latent Label Shift

Jul 26, 2022
Manley Roberts, Pranav Mani, Saurabh Garg, Zachary C. Lipton

Figure 1 for Unsupervised Learning under Latent Label Shift

Figure 2 for Unsupervised Learning under Latent Label Shift

Figure 3 for Unsupervised Learning under Latent Label Shift

Figure 4 for Unsupervised Learning under Latent Label Shift

* Manley Roberts and Pranav Mani contributed equally to this work

Access Paper or Ask Questions

Deconstructing Distributions: A Pointwise Framework of Learning

Feb 20, 2022
Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran

Figure 1 for Deconstructing Distributions: A Pointwise Framework of Learning

Figure 2 for Deconstructing Distributions: A Pointwise Framework of Learning

Figure 3 for Deconstructing Distributions: A Pointwise Framework of Learning

Figure 4 for Deconstructing Distributions: A Pointwise Framework of Learning

* GK and NG contributed equally

Access Paper or Ask Questions

Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

Feb 09, 2022
Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton, Behnam Neyshabur, Hanie Sedghi

Figure 1 for Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

Figure 2 for Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

Figure 3 for Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

Figure 4 for Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

* Accepted at ICLR 2022

Access Paper or Ask Questions