SakethaNath N Jagarlapudi — accepted AI-conference papers

2024

Consistent Optimal Transport with Empirical Conditional Measures

Piyushi Manupriya, Rachit K. Das, Sayantan Biswas, SakethaNath N Jagarlapudi

AISTATS 2024poster

Given samples from two joint distributions, we consider the problem of Optimal Transportation (OT) between them when conditioned on a common variable. We focus on the general setting where the conditioned variable may be continuous, and the marginals of this variable in the two joint distributions m…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2022

Improving Attribution Methods by Learning Submodular Functions

Piyushi Manupriya, Tarun Ram Menta, Sakethanath N. Jagarlapudi, Vineeth N. Balasubramanian

AISTATS 2022poster

This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods. Submodular scores are natural for attribution as they are known to accurately model the principle of diminishing returns. A new formulation for…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗