About Me
I am currently an AI Resident at Google Research NYC working with the Algorithms & Optimization Team.
I recently finished my Ph.D. in Electrical Engineering at Stanford University, where I was fortunate to be advised by Mohsen Bayati. My research lies at the intersection of operations research, machine learning, and statistics. In particular, I am interested in online decision making, contextual bandits, and causal inference.
Before joining Google, I was a lecturer at Stanford Graduate School of Business, where I co-taught OIT 245 (Optimization and Simulation Modeling) and OIT 367 (Business Intelligence from Big Data).
I spent summer 2018 at Microsoft Research New England with Vasilis Syrgkanis and Greg Lewis as a research intern. Previously, I obtained bachelor degrees in Electrical Engineering and Mathematics both from Sharif University of Technology.
News
Research Interests
Contextual multi-armed bandit
Causal inference
Personalized and data-driven decision-making
Machine learning and optimization
Statistics
Working Papers
M. Bayati, N. Hamidi, R. Johari, and K. Khosravi, Optimal and Greedy Algorithms for Multi-Armed Bandits with Many Arms
K. Khosravi, G. Lewis, and V. Syrgkanis, Non-Parametric Inference Adaptive to Intrinsic Dimension
S. Athey, M. Bayati, N. Doudchenko, G. Imbens, and K. Khosravi, Matrix Completion Methods for Causal Panel Data Models, Package
Published Papers
H. Bastani, M. Bayati, and K. Khosravi, Mostly Exploration-Free Algorithms for Contextual Bandits, Management Science (forthcoming)
J.C. Duchi, K. Khosravi, and F. Ruan, Multiclass classification, information, divergence and surrogate risk, Annals of Statistics 46(6B):3246-3275, 2018
H. Inan, K. Khosravi, and R. Socher, Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling, ICLR 2017
Dissertations
|