19 citations · 65 across the 17 of their papers we have counts for
6 papers · 2 filters
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…
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…
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.…
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…
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…
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…