no code implementations • 7 Dec 2022 • Safinah Ali, Sohini Upadhyay, Gaurush Hiranandani, Elena L. Glassman, Oluwasanmi Koyejo
Specifically, we create a web-based ME interface and conduct a user study that elicits users' preferred metrics in a binary classification setting.
no code implementations • 15 May 2022 • Jessica Dai, Sohini Upadhyay, Ulrich Aivodji, Stephen H. Bach, Himabindu Lakkaraju
We then leverage these properties to propose a novel evaluation framework which can quantitatively measure disparities in the quality of explanations output by state-of-the-art methods.
no code implementations • 9 Aug 2021 • Sohini Upadhyay, Vatche Isahagian, Vinod Muthusamy, Yara Rizk
AI business process applications automate high-stakes business decisions where there is an increasing demand to justify or explain the rationale behind algorithmic decisions.
no code implementations • 24 Jun 2021 • Jessica Dai, Sohini Upadhyay, Stephen H. Bach, Himabindu Lakkaraju
In situations where explanations of black-box models may be useful, the fairness of the black-box is also often a relevant concern.
no code implementations • 18 Jun 2021 • Martin Pawelczyk, Chirag Agarwal, Shalmali Joshi, Sohini Upadhyay, Himabindu Lakkaraju
As machine learning (ML) models become more widely deployed in high-stakes applications, counterfactual explanations have emerged as key tools for providing actionable model explanations in practice.
no code implementations • NeurIPS 2021 • Sohini Upadhyay, Shalmali Joshi, Himabindu Lakkaraju
To address this problem, we propose a novel framework, RObust Algorithmic Recourse (ROAR), that leverages adversarial training for finding recourses that are robust to model shifts.
no code implementations • 21 Feb 2021 • Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Zhiwei Steven Wu, Himabindu Lakkaraju
As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a post hoc manner.
no code implementations • ICLR Workshop LLD 2019 • Sohini Upadhyay, Mikhail Yurochkin, Mayank Agarwal, Yasaman Khazaeni, DjallelBouneffouf
We formulate a new problem at the intersectionof semi-supervised learning and contextual bandits, motivated by several applications including clini-cal trials and ad recommendations.
no code implementations • 15 Oct 2020 • Djallel Bouneffouf, Raphaël Féraud, Sohini Upadhyay, Yasaman Khazaeni, Irina Rish
In this paper, we analyze and extend an online learning framework known as Context-Attentive Bandit, motivated by various practical applications, from medical diagnosis to dialog systems, where due to observation costs only a small subset of a potentially large number of context variables can be observed at each iteration;however, the agent has a freedom to choose which variables to observe.
no code implementations • 13 Jul 2020 • Djallel Bouneffouf, Sohini Upadhyay, Yasaman Khazaeni
We consider a novel variant of the contextual bandit problem (i. e., the multi-armed bandit with side-information, or context, available to a decision-maker) where the reward associated with each context-based decision may not always be observed("missing rewards").
no code implementations • 22 Jun 2019 • Sohini Upadhyay, Mayank Agarwal, Djallel Bounneffouf, Yasaman Khazaeni
Building multi-domain AI agents is a challenging task and an open problem in the area of AI.