Vashist Avadhanula

Research Scientist - Core Data Science

I am a research scientist on the Core Data Science team. I have recently graduated from Columbia University with a PhD in decision, risk and operations. I worked on online algorithms for learning choice models. As part of my thesis work, I have also collaborated with Flipkart, India’s largest e-commerce firm in improving their product recommendations. I am broadly interested in developing tractable approaches for decision making under uncertainty. I am particularly excited about applying these ideas to improve business products at Facebook.


Machine learning, optimization, multi-armed bandits and fairness in machine learning

Latest Publications

The Web Conference - April 21, 2021

Stochastic bandits for multi-platform budget optimization in online advertising

Vashist Avadhanula, Riccardo Colini Baldeschi, Stefano Leonardi, Karthik Abinav Sankararaman, Okke Schrijvers

AISTATS - April 13, 2021

Multi-armed Bandits with Cost Subsidy

Deeksha Sinha, Karthik Abinav Sankararaman, Abbas Kazerouni, Vashist Avadhanula

Workshop on Safety and Robustness in Decision Making at NeurIPS - December 2, 2019

Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints

Sam Daulton, Shaun Singh, Vashist Avadhanula, Drew Dimmery, Eytan Bakshy