24 citations · 87 across the 36 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021
Omnipredictors
Parikshit Gopalan, Adam Tauman Kalai, Omer Reingold +2
Loss minimization is a dominant paradigm in machine learning, where a predictor is trained to minimize some loss function that depends on an uncertain event (e.g., "will it rain to…
cs.LG2021
Multicalibrated Partitions for Importance Weights
Parikshit Gopalan, Omer Reingold, Vatsal Sharan +1
The ratio between the probability that two distributions and give to points are known as importance weights or propensity scores and play a fundamental role in many dif…