Benjamin Van Roy: Students

Current Students

Anmol Kagrecha
Henrik Marklund
Wanqiao Xu
Yifan Zhu

Former Doctoral Students

Hong Jun Jeon (2025)
Tesla
Dissertation: Information-Theoretic Foundations for Machine Learning

Saurabh Kumar (2025)
Google DeepMind
Dissertation: Compute-Constrained Continual Learning: Foundations and Algorithms

Yueyang Liu (2024)
Rice University
Dissertation: Non-Stationary Bandit Learning: Algorithm Design and Theory

Dilip Arumugam (2024)
Princeton
Dissertation: Deciding What to Learn in Complex Environments

Zheqing (Bill) Zhu (2023)
Pokee AI
Dissertation: Efficient Deep Reinforcement Learning for Recommender Systems

Shi Dong (2022)
xAI
Dissertation: Efficient Reinforcement Learning with Agent States

Vikranth Dwaracherla (2021)
Google DeepMind
Dissertation: Posterior Sampling for Efficient Reinforcement Learning

Xiuyuan (Lucy) Lu (2020)]
Google DeepMind
Dissertation: Information-Theoretic Regret Bounds for Reinforcement Learning

Abbas Kazerouni (2019)
Meta
Dissertation: Efficient Exploration in Bandit and Reinforcement Learning

Maria Dimakopoulou (2018)
Uber
Dissertation: Coordinated Exploration in Concurrent Reinforcement Learning

Ian Osband (2016)
Google DeepMind
Dissertation: Deep Exploration via Value Function Randomization

Dan Russo (2015)
Columbia University
Dissertation: Efficient Learning and Experimentation in Sequential Optimization

Zheng Wen (2014)
OpenAI
Dissertation: Efficient Reinforcement Learning with Value Function Generalization

Waraporn Tongprasit (2013)
Morgan Stanley
Dissertation: Empirical Analysis of the Impact of Tick Sizes on Exchange Efficiency

Beomsoo Park (2012)
Morgan Stanley
Dissertation: Strategic and Adaptive Execution

Yi-Hao (Edward) Kao (2012)
Two Sigma Investments
Dissertation: Directed Learning

Michael Padilla (2011)
Knock
Dissertation: Intermediated Blind Portfolio Auctions

Xiang (Robbie) Yan (2009)
Advance.AI
Dissertation: Manipulation Robustness of Collaborative Filtering Systems

Ciamac Moallemi (2007)
Columbia University
Dissertation: A Message-Passing Paradigm for Optimization

Vivek Farias (2007)
Massachusetts Institute of Technology
Dissertation: Revenue Management Beyond “Estimate, Then Optimize”

Gabriel Weintraub (2006)
Stanford University
Dissertation: Industry Dynamics, Investment, and Market Structure

Jiarui (Jared) Han (2005)
Citadel Investment Group
Dissertation: Dynamic Portfolio Management - An Approximate Linear Programming Approach

Kahn Mason (2005)
Jane Street
Dissertation: Detecting Colluders in PageRank - Finding Slow Mixing States in a Markov Chain

David S. Choi (2003)
Carnegie Mellon University
Dissertation: Optimization for Value Function Approximation

Paat Rusmevichientong (2003)
University of Southern California
Dissertation: A Non-Parametric Approach to Multi-Product Pricing

Daniela P. de Farias (2002)
Daniela & Luis Tango Argentino
Dissertation: The Linear Programming Approach to Approximate Dynamic Programming

Former MS Students

Nick Choo (2006)
Quantitative Investment Firm

Recognition

Wanqiao Xu won the 2024 Reinforcement Learning Conference Outstanding Paper Award on the Theory of RL.
Shi Dong won the 2021 INFORMS Nicholson Student Paper Competition.
Ian Osband won the second place prize of the 2017 INFORMS Dantzig Dissertation Award.
Dan Russo won the 2014 INFORMS Nicholson Student Paper Competition.
Yi-Hao Kao received an honorable mention in the 2012 INFORMS Nicholson Student Paper Competition.
Yi-Hao Kao was selected as a finalist for the 2012 INFORMS Data Mining Best Student Paper Award.
Michael Padilla won the 2010 INFORMS Financial Services Section Best Student Research Paper Award.
Xiang Yan was selected as a finalist in the 2009 INFORMS Nicholson Student Paper Competition.
Vivek Farias won the second place prize in the 2006 MSOM Student Paper Competition.
Paat Rusmevichientong won the 2003 INFORMS Dantzig Dissertation Award.
Daniela de Farias won the 2002 INFORMS Dantzig Dissertation Award.