166 citations · 1.4k across the 47 of their papers we have counts for
4 papers · 1 filter
Independence Properties of Generalized Submodular Information Measures
Himanshu Asnani, Jeff Bilmes, Rishabh Iyer
Recently a class of generalized information measures was defined on sets of items parametrized by submodular functions. In this paper, we propose and study various notions of indep…
An Effective Baseline for Robustness to Distributional Shift
Sunil Thulasidasan, Sushil Thapa, Sayera Dhaubhadel +3
Refraining from confidently predicting when faced with categories of inputs different from those seen during training is an important requirement for the safe deployment of deep le…
Submodular Mutual Information for Targeted Data Subset Selection
Suraj Kothawade, Vishal Kaushal, Ganesh Ramakrishnan +2
With the rapid growth of data, it is becoming increasingly difficult to train or improve deep learning models with the right subset of data. We show that this problem can be effect…
PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection
Suraj Kothawade, Vishal Kaushal, Ganesh Ramakrishnan +2
With ever-increasing dataset sizes, subset selection techniques are becoming increasingly important for a plethora of tasks. It is often necessary to guide the subset selection to…