Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Fair Data Integration

Jun 10, 2020
Sainyam Galhotra, Karthikeyan Shanmugam, Prasanna Sattigeri, Kush R. Varshney


  Access Paper or Ask Questions

Combinatorial Black-Box Optimization with Expert Advice

Jun 06, 2020
Hamid Dadkhahi, Karthikeyan Shanmugam, Jesus Rios, Payel Das, Samuel Hoffman, Troy David Loeffler, Subramanian Sankaranarayanan


  Access Paper or Ask Questions

Invariant Risk Minimization Games

Mar 18, 2020
Kartik Ahuja, Karthikeyan Shanmugam, Kush R. Varshney, Amit Dhurandhar


  Access Paper or Ask Questions

A Multi-Channel Neural Graphical Event Model with Negative Evidence

Feb 21, 2020
Tian Gao, Dharmashankar Subramanian, Karthikeyan Shanmugam, Debarun Bhattacharjya, Nicholas Mattei

* AAAI 2020 

  Access Paper or Ask Questions

Warm Starting Bandits with Side Information from Confounded Data

Feb 19, 2020
Nihal Sharma, Soumya Basu, Karthikeyan Shanmugam, Sanjay Shakkottai


  Access Paper or Ask Questions

Learning Global Transparent Models from Local Contrastive Explanations

Feb 19, 2020
Tejaswini Pedapati, Avinash Balakrishnan, Karthikeyan Shanmugam, Amit Dhurandhar


  Access Paper or Ask Questions

Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes

Feb 10, 2020
Zaiwei Chen, Siva Theja Maguluri, Sanjay Shakkottai, Karthikeyan Shanmugam

* Total 27 pages, main paper 13 pages, references 2 pages, Appendix 12 pages 

  Access Paper or Ask Questions

Differentially Private Distributed Data Summarization under Covariate Shift

Oct 28, 2019
Kanthi Sarpatwar, Karthikeyan Shanmugam, Venkata Sitaramagiridharganesh Ganapavarapu, Ashish Jagmohan, Roman Vaculin

* To appear in the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada 

  Access Paper or Ask Questions

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

Sep 14, 2019
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovińá, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang


  Access Paper or Ask Questions

Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions

Aug 23, 2019
Matthew Faw, Rajat Sen, Karthikeyan Shanmugam, Constantine Caramanis, Sanjay Shakkottai


  Access Paper or Ask Questions

Model Agnostic Contrastive Explanations for Structured Data

May 31, 2019
Amit Dhurandhar, Tejaswini Pedapati, Avinash Balakrishnan, Pin-Yu Chen, Karthikeyan Shanmugam, Ruchir Puri


  Access Paper or Ask Questions

Leveraging Simple Model Predictions for Enhancing its Performance

May 30, 2019
Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss


  Access Paper or Ask Questions

Generating Contrastive Explanations with Monotonic Attribute Functions

May 29, 2019
Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam, Chun-Chen Tu


  Access Paper or Ask Questions

Size of Interventional Markov Equivalence Classes in Random DAG Models

Mar 05, 2019
Dmitriy Katz, Karthikeyan Shanmugam, Chandler Squires, Caroline Uhler

* 19 pages, 5 figures. Accepted to AISTATS 2019 

  Access Paper or Ask Questions

Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives

Oct 29, 2018
Amit Dhurandhar, Pin-Yu Chen, Ronny Luss, Chun-Chen Tu, Paishun Ting, Karthikeyan Shanmugam, Payel Das


  Access Paper or Ask Questions

TIP: Typifying the Interpretability of Procedures

Oct 29, 2018
Amit Dhurandhar, Vijay Iyengar, Ronny Luss, Karthikeyan Shanmugam


  Access Paper or Ask Questions

Improving Simple Models with Confidence Profiles

Jul 19, 2018
Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss, Peder Olsen

* 16 pages 

  Access Paper or Ask Questions

Mimic and Classify : A meta-algorithm for Conditional Independence Testing

Jun 25, 2018
Rajat Sen, Karthikeyan Shanmugam, Himanshu Asnani, Arman Rahimzamani, Sreeram Kannan

* 16 pages, 2 figures 

  Access Paper or Ask Questions

Structure Learning from Time Series with False Discovery Control

May 24, 2018
Bernat Guillen Pegueroles, Bhanukiran Vinzamuri, Karthikeyan Shanmugam, Steve Hedden, Jonathan D. Moyer, Kush R. Varshney


  Access Paper or Ask Questions

Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes

May 14, 2018
Tongfei Chen, JiŇô√≠ Navr√°til, Vijay Iyengar, Karthikeyan Shanmugam


  Access Paper or Ask Questions

Contextual Bandits with Stochastic Experts

Feb 23, 2018
Rajat Sen, Karthikeyan Shanmugam, Sanjay Shakkottai

* 20 pages, 2 Figures, Accepted for publication in AISTATS 2018 

  Access Paper or Ask Questions

Model-Powered Conditional Independence Test

Sep 18, 2017
Rajat Sen, Ananda Theertha Suresh, Karthikeyan Shanmugam, Alexandros G. Dimakis, Sanjay Shakkottai

* 19 Pages, 2 figures, Accepted for publication in NIPS 2017 

  Access Paper or Ask Questions

A Formal Framework to Characterize Interpretability of Procedures

Jul 12, 2017
Amit Dhurandhar, Vijay Iyengar, Ronny Luss, Karthikeyan Shanmugam

* presented at 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017), Sydney, NSW, Australia 

  Access Paper or Ask Questions

Identifying Best Interventions through Online Importance Sampling

Mar 09, 2017
Rajat Sen, Karthikeyan Shanmugam, Alexandros G. Dimakis, Sanjay Shakkottai

* 30 pages, 11 figures 

  Access Paper or Ask Questions

Sparse Quadratic Logistic Regression in Sub-quadratic Time

Mar 08, 2017
Karthikeyan Shanmugam, Murat Kocaoglu, Alexandros G. Dimakis, Sujay Sanghavi


  Access Paper or Ask Questions

Contextual Bandits with Latent Confounders: An NMF Approach

Oct 27, 2016
Rajat Sen, Karthikeyan Shanmugam, Murat Kocaoglu, Alexandros G. Dimakis, Sanjay Shakkottai

* 37 pages, 2 figures 

  Access Paper or Ask Questions