3 citations · 5 across the 2 of their papers we have counts for
3 papers
cs.LG2020★ 3 cited
The Penalty Imposed by Ablated Data Augmentation
Frederick Liu, Amir Najmi, Mukund Sundararajan
There is a set of data augmentation techniques that ablate parts of the input at random. These include input dropout, cutout, and random erasing. We term these techniques ablated d…
cs.AI2019
The many Shapley values for model explanation
Mukund Sundararajan, Amir Najmi
The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The use of the Shapley value is justified by…
math.ST2019★ 2 cited
Unbiased variance reduction in randomized experiments
Reza Hosseini, Amir Najmi
This paper develops a flexible method for decreasing the variance of estimators for complex experiment effect metrics (e.g. ratio metrics) while retaining asymptotic unbiasedness.…