activity
20182022
most citedMixture Proportion Estimation and PU Learning: A Modern Approach

5 citations · 12 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

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.LG20223 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.LG20215 cited

Mixture Proportion Estimation and PU Learning: A Modern Approach

Saurabh Garg, Yifan Wu, Alex Smola +2

Given only positive examples and unlabeled examples (from both positive and negative classes), we might hope nevertheless to estimate an accurate positive-versus-negative classifie…

cs.LG2021

RATT: Leveraging Unlabeled Data to Guarantee Generalization

Saurabh Garg, Sivaraman Balakrishnan, J. Zico Kolter +1

To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on th…

cs.LG2020

A Unified View of Label Shift Estimation

Saurabh Garg, Yifan Wu, Sivaraman Balakrishnan +1

Under label shift, the label distribution p(y) might change but the class-conditional distributions p(x|y) do not. There are two dominant approaches for estimating the label margin…