270 citations · 835 across the 84 of their papers we have counts for
7 papers · 1 filter
Improving Simple Models with Confidence Profiles
Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss +1
In this paper, we propose a new method called ProfWeight for transferring information from a pre-trained deep neural network that has a high test accuracy to a simpler interpretabl…
Mimic and Classify : A meta-algorithm for Conditional Independence Testing
Rajat Sen, Karthikeyan Shanmugam, Himanshu Asnani +2
Given independent samples generated from the joint distribution , we study the problem of Conditional Independence (CI-Testing), i.e., whether…
Structure Learning from Time Series with False Discovery Control
Bernat Guillen Pegueroles, Bhanukiran Vinzamuri, Karthikeyan Shanmugam +3
We consider the Granger causal structure learning problem from time series data. Granger causal algorithms predict a 'Granger causal effect' between two variables by testing if pre…
Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes
Tongfei Chen, Jiří Navrátil, Vijay Iyengar +1
We propose a novel confidence scoring mechanism for deep neural networks based on a two-model paradigm involving a base model and a meta-model. The confidence score is learned by t…
Contextual Bandits with Stochastic Experts
Rajat Sen, Karthikeyan Shanmugam, Nihal Sharma +1
We consider the problem of contextual bandits with stochastic experts, which is a variation of the traditional stochastic contextual bandit with experts problem. In our problem set…
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
Amit Dhurandhar, Pin-Yu Chen, Ronny Luss +4
In this paper we propose a novel method that provides contrastive explanations justifying the classification of an input by a black box classifier such as a deep neural network. Gi…
From Centralized to Decentralized Coded Caching
Yitao Chen, Karthikeyan Shanmugam, Alexandros G. Dimakis
We consider the problem of designing decentralized schemes for coded caching. In this problem there are users each caching files out of a library of total files. The qu…