I am a PhD candidate in Computer Science at Cornell University broadly working in the area of machine learning and algorithms. More specifically, I am interested in problems around counterfactual policy learning and evaluation in addition to thinking about questions on fairness, interpretability and transparency in such settings. I am extremely fortunate to be advised by Thorsten Joachims.
In the past, I graduated from Texas A&M University in May 2018 with a B.S. in Computer Science (summa cum laude), completing an ACE Scholars degree with an honors thesis supervised by Dr. Jennifer Welch. I’ve also worked in engineering at Facebook, an intern at Nextdoor, and an intern at Apple. During undergrad, I also helped run TAMUhack.
Policy-gradient training of fair and unbiased ranking functions [arXiv]
Himank Yadav*, Zhengxiao Du*, Thorsten Joachims
Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.
Detecting Failures in an Asynchronous System That Never Stops Changing [thesis]
Dissertation. Texas A&M University.
Wide Baseline Matching [report]
Qianqian Wang, Himank Yadav, Wenqi Xian
Counters: Identifying and Summarizing Opposing Media Articles [report]
Himank Yadav, Katherine Van Koevering
Applicability of Language Models to Fact Checking [report]
George Karagiannis, FlorianSuri-Payer, Himank Yadav