Search Results for author: Piyushi Manupriya

Found 3 papers, 1 papers with code

Improving Attribution Methods by Learning Submodular Functions

no code implementations19 Apr 2021 Piyushi Manupriya, Saketha Nath Jagarlapudi, Tarun Ram Menta, Vineeth N Balasubramanian

This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods.

Integral Probability Metric based Regularization for Optimal Transport

no code implementations10 Nov 2020 Piyushi Manupriya, J. Saketha Nath, Pratik Jawanpuria

Also, in the special case where the regularization is squared maximum mean discrepancy based, the proposed OT variant, as well as the corresponding Barycenter formulation, turn out to be those of minimizing a convex quadratic subject to non-negativity/simplex constraints and hence can be solved efficiently.

Neural Network Attributions: A Causal Perspective

1 code implementation6 Feb 2019 Aditya Chattopadhyay, Piyushi Manupriya, Anirban Sarkar, Vineeth N. Balasubramanian

We propose a new attribution method for neural networks developed using first principles of causality (to the best of our knowledge, the first such).

Cannot find the paper you are looking for? You can Submit a new open access paper.