Picture for Kush R. Varshney

Kush R. Varshney

Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

Dec 13, 2022
Prasanna Sattigeri, Soumya Ghosh, Inkit Padhi, Pierre Dognin, Kush R. Varshney

Figure 1 for Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

Figure 2 for Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

Figure 3 for Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

Figure 4 for Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

* Accepted at Neurips 2022

Access Paper or Ask Questions

On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Nov 02, 2022
Dennis Wei, Rahul Nair, Amit Dhurandhar, Kush R. Varshney, Elizabeth M. Daly, Moninder Singh

Figure 1 for On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Figure 2 for On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Figure 3 for On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Figure 4 for On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

* Published at NeurIPS 2022

Access Paper or Ask Questions

Human-Centered Explainable AI (XAI): From Algorithms to User Experiences

Oct 23, 2021
Q. Vera Liao, Kush R. Varshney

Figure 1 for Human-Centered Explainable AI (XAI): From Algorithms to User Experiences

Figure 2 for Human-Centered Explainable AI (XAI): From Algorithms to User Experiences

Figure 3 for Human-Centered Explainable AI (XAI): From Algorithms to User Experiences

Figure 4 for Human-Centered Explainable AI (XAI): From Algorithms to User Experiences

* draft for a book chapter

Access Paper or Ask Questions

An Empirical Study of Accuracy, Fairness, Explainability, Distributional Robustness, and Adversarial Robustness

Sep 29, 2021
Moninder Singh, Gevorg Ghalachyan, Kush R. Varshney, Reginald E. Bryant

Figure 1 for An Empirical Study of Accuracy, Fairness, Explainability, Distributional Robustness, and Adversarial Robustness

Figure 2 for An Empirical Study of Accuracy, Fairness, Explainability, Distributional Robustness, and Adversarial Robustness

Figure 3 for An Empirical Study of Accuracy, Fairness, Explainability, Distributional Robustness, and Adversarial Robustness

* presented at the 2021 KDD Workshop on Measures and Best Practices for Responsible AI

Access Paper or Ask Questions