Learning models with uniform performance via distributionally robust optimization
Work
Year: 2021
Type: article
Abstract: A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts or unmode... more
Source: The Annals of Statistics
Authors John C. Duchi, Hongseok Namkoong
Institution Stanford University
Cites: 79
Cited by: 83
Related to: 10
FWCI: 12.08
Citation percentile (by year/subfield): 99.98
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green