activity
20172023
most citedLeveraging Unlabeled Data to Predict Out-of-Distribution Performance

19 citations · 65 across the 17 of their papers we have counts for

collaborators
Showing 2022 · cs.LGShow all

6 papers · 2 filters

cs.LG2022

Disentangling the Mechanisms Behind Implicit Regularization in SGD

Zachary Novack, Simran Kaur, Tanya Marwah +2

A number of competing hypotheses have been proposed to explain why small-batch Stochastic Gradient Descent (SGD)leads to improved generalization over the full-batch regime, with re…

cs.LG2022★ 3 cited

Characterizing Datapoints via Second-Split Forgetting

Pratyush Maini, Saurabh Garg, Zachary C. Lipton +1

Researchers investigating example hardness have increasingly focused on the dynamics by which neural networks learn and forget examples throughout training. Popular metrics derived…

cs.LG2022★ 2 cited

Unsupervised Learning under Latent Label Shift

Manley Roberts, Pranav Mani, Saurabh Garg +1

What sorts of structure might enable a learner to discover classes from unlabeled data? Traditional approaches rely on feature-space similarity and heroic assumptions on the data.…

cs.LG2022★ 7 cited

Domain Adaptation under Open Set Label Shift

Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton

We introduce the problem of domain adaptation under Open Set Label Shift (OSLS) where the label distribution can change arbitrarily and a new class may arrive during deployment, bu…

cs.LG2022★ 1 cited

Deconstructing Distributions: A Pointwise Framework of Learning

Gal Kaplun, Nikhil Ghosh, Saurabh Garg +2

In machine learning, we traditionally evaluate the performance of a single model, averaged over a collection of test inputs. In this work, we propose a new approach: we measure the…

cs.LG2022★ 19 cited

Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton +2

Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions that may cause performance drops. In this work…