349, Bill and Melinda Gates Hall
107 Hoy Rd
I am a Ph.D. Candidate in Computer Science at Cornell University in Ithaca, NY. I am advised by Thorsten Joachims. I am fortunate to have Solon Barocas, Karthik Sridharan, and David Mimno on my dissertation committee.
My research spans the broad areas of Machine Learning, Recommender Systems, and Information Retrieval. My research focuses on:
- Building machine learning models and algorithms to learn from interactive user feedback in user-facing platforms such as search and recommendation.
- Fairness and Responsibility aspects of Recommender Systems considering fair distribution of opportunity for both users as well as the items.
Through my research, I envision search and recommendation systems to form the foundation of economically sustainable multistakeholder online platforms that ensure utility, fairness, and safety for the users as well as the creators and producers.
During my Ph.D., I have completed internships at Google Brain, Facebook Research, and Microsoft Research (NYC and Montreal) where I had the opportunity to collaborate closely with Alex Beutel, Fernando Diaz, Khalid El-Arini, John Langford. Previously, I was an undergraduate student at the Indian Institute of Technology (IIT) Kanpur and also spent a summer at Carnegie Mellon University doing research on Natural Language Processing. You can find more information on the resume and cv.
|Nov 1, 2020||I am on the job market for research positions in the industry. Find my resume here, cv here, research statement here or reach out via email for more relevant material.|
|Sep 20, 2020||
Our new work on Building Healthy Recommendation Sequences for Everyone: A Safe Reinforcement Learning Approach has been accepted at FAccTRec workshop on Responsible Recommendation at ACM RecSys 2020 to be held from September 22-26, 2020.
This is joint work with my collaborators at Google Research.
|Aug 19, 2020||Communications of the ACM (CACM) and Cornell Chronicle covered a story about our ACM SIGIR 2020 paper Controlling Fairness and Bias in Dynamic Learning-to-Rank.|
|Jul 22, 2020||Our paper Controlling Fairness and Bias in Dynamic Learning-to-Rank has been awarded the Best Paper Award at the ACM SIGIR 2020 conference that was held virtually.|
selected publicationsFind more information on the publications page and google scholar.
* contributed equally.
- KDDFairness of Exposure in RankingsIn In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, UK, 2018.
- NeurIPSPolicy learning for fairness in rankingIn Neural Information Processing Systems (NeurIPS), 2019.
- SIGIRControlling Fairness and Bias in Dynamic Learning-to-RankIn Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval, 2020. Best Paper Award
- RecSys WorkshopBuilding Healthy Recommendation Sequences for Everyone: A Safe Reinforcement Learning ApproachIn FAccTRec Workshop at ACM RecSyS, 2020.