285 citations · 358 across the 8 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 285 cited
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…
cs.LG2020★ 28 cited
Adaptive Risk Minimization: Learning to Adapt to Domain Shift
Marvin Zhang, Henrik Marklund, Nikita Dhawan +3
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violate…