2.3k citations · 2.6k across the 10 of their papers we have counts for
3 papers · 1 filter
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Pang Wei Koh, Shiori Sagawa, Henrik Marklund +20
Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the…
Selective Classification Can Magnify Disparities Across Groups
Erik Jones, Shiori Sagawa, Pang Wei Koh +2
Selective classification, in which models can abstain on uncertain predictions, is a natural approach to improving accuracy in settings where errors are costly but abstentions are…
An Investigation of Why Overparameterization Exacerbates Spurious Correlations
Shiori Sagawa, Aditi Raghunathan, Pang Wei Koh +1
We study why overparameterization -- increasing model size well beyond the point of zero training error -- can hurt test error on minority groups despite improving average test err…