Sean Sinclair

Home Publications Talks Teaching Other

	Sean Sinclair is an Assistant Professor at Northwestern University in the Industrial Engineering and Management Sciences department. Previously he was a postdoctoral associate under Devavrat Shah and Ali Jadbabaie at Massachusetts Institute of Technology. Sean completed his PhD at Cornell University coadvised by Christina Lee Yu and Siddhartha Banerjee. His research focuses on developing algorithms for data-driven sequential decision making in societal applications. He bridges algorithmic techniques in reinforcement learning to an operations management perspective with an emphasis on models, data uncertainty, and objectives. Recent contributions include instance-specific optimal regret guarantees for nonparametric reinforcement learning, Pareto-optimal fair resource allocation, and data-efficient algorithms for cloud compute allocations. Complementing this, he also designs open-source code instrumentation and methodology to empirically analyze the multi-criteria performance of algorithms on these problems. He graduated with a B.S. in Honours Mathematics and Computer Science from McGill University where he worked on a project with Tony Humphries. Before returning to graduate school he spent two and a half years teaching mathematics, science, and English in a small community in rural Ghana with the Peace Corps, and after worked at National Life as a financial analyst. Prospective Students: I am actively looking for Ph.D. students. However, Ph.D. admissions to Northwestern IEMS are handled at a department level and not by me individually. Prospective students with undergraduate backgrounds in applied mathematics, computer science, economics, or statistics are encouraged to contact me by email after reading here. See here for my advising commitments and expectations. Office: D237 Northwestern University Technological Institute Email: sean dot sinclair at northwestern.edu [CV] [Google Scholar] [Github] [Twitter] [LinkedIn]

Sean Sinclair is an Assistant Professor at Northwestern University in the Industrial Engineering and Management Sciences department. Previously he was a postdoctoral associate under Devavrat Shah and Ali Jadbabaie at Massachusetts Institute of Technology. Sean completed his PhD at Cornell University coadvised by Christina Lee Yu and Siddhartha Banerjee. His research focuses on developing algorithms for data-driven sequential decision making in societal applications. He bridges algorithmic techniques in reinforcement learning to an operations management perspective with an emphasis on models, data uncertainty, and objectives. Recent contributions include instance-specific optimal regret guarantees for nonparametric reinforcement learning, Pareto-optimal fair resource allocation, and data-efficient algorithms for cloud compute allocations. Complementing this, he also designs open-source code instrumentation and methodology to empirically analyze the multi-criteria performance of algorithms on these problems.

He graduated with a B.S. in Honours Mathematics and Computer Science from McGill University where he worked on a project with Tony Humphries. Before returning to graduate school he spent two and a half years teaching mathematics, science, and English in a small community in rural Ghana with the Peace Corps, and after worked at National Life as a financial analyst.

Prospective Students: I am actively looking for Ph.D. students. However, Ph.D. admissions to Northwestern IEMS are handled at a department level and not by me individually. Prospective students with undergraduate backgrounds in applied mathematics, computer science, economics, or statistics are encouraged to contact me by email after reading here. See here for my advising commitments and expectations.

Office: D237 Northwestern University Technological Institute
Email: sean dot sinclair at northwestern.edu
[CV] [Google Scholar] [Github] [Twitter] [LinkedIn]

News

August 2024: New preprint of our paper "Multi-Objective LQR with Linear Scalarization" is available on arXiv.
July 2024: Started my position at Northwestern University in IEMS. Please reach out if you are in the area!
February 2024: New preprint of our paper "Online Fair Allocation of Perishable Resources" is on SSRN!
October 2023: Awarded a finalist for the George Dantzig PhD Dissertation award!
August 2023: Started my postdoc position at MID in Lids advised by Devavrat Shah and Ali Jadbabaie. Please reach out if you are in the Boston area and want to talk!
May 2023: My paper, "Hindsight Learning in MDPs with Exogenous Inputs" was accepted in ICML 2023!
April 2023: My paper, "Online Fair Allocation of Perishable Resources" was accepted in SIGMETRICS 2023!
March 2023: Accepted a postdoc position at MIT in LIDS advised by Devavrat Shah and Ali Jadbabaie!
February 2023: Accepted a position at Northwestern University in the Industrial Engineering and Management Science department as an assistant professor starting Fall 2024!
October 2022: My papers "Sequential Fair Allocation: Achieving the Optimal Envy-Efficiency Tradeoff Curve" and "Adaptive Discretization in Online Reinforcement Learning" were accepted to Operations Research!
September 2022: My paper, "Sequential Fair Allocation: Achieving the Optimal Envy-Efficiency Tradeoff Curve" is a finalist for the 2022 INFORMS DEI Best Student Paper Award!
August 2022: On August 23 I will be speaking at the Data Driven Decision Processes Bootcamp on Online Reinforcement Learning and Regret.
June 2022: In August 15-18 I will be speaking at the Summer Bootcamp at Kelogg on RL in Operations.
June 2022: This Fall I'll be a visiting graduate student at Simons Institute for the Data-Driven Decision Processes program.
May 2022: In June I'll be speaking at the Workshop on Algorithms for Learning and Economics and participating in a panel on Socially Responsible ML.

Selected Publications

Hindsight Learning in MDPs with Exogenous Inputs [arXiv] ICML 2023

Sean R. Sinclair, Felipe Frujeri, Ching-An Cheng, Luke Marshall, Hugo Barbalho, Jingling Li, Jennifer Neville, Ishai Menache, and Adith Swaminathan.

Adaptive Discretization in Online Reinforcement Learning [arXiv] Operations Research 2022

Sean R. Sinclair, Siddhartha Banerjee, and Christina Lee Yu.

Sequential Fair Allocation: Achieving the Optimal Envy-Efficiency Tradeoff Curve [arXiv] [video] Operations Research 2022

Sean R. Sinclair, Gauri Jain, Siddhartha Banerjee, and Christina Lee Yu.

Finalist for the 2022 INFORMS DEI Best Student Paper Award

Hindsight Learning in MDPs with Exogenous Inputs [arXiv]	ICML 2023
Sean R. Sinclair, Felipe Frujeri, Ching-An Cheng, Luke Marshall, Hugo Barbalho, Jingling Li, Jennifer Neville, Ishai Menache, and Adith Swaminathan.

Adaptive Discretization in Online Reinforcement Learning [arXiv]	Operations Research 2022
Sean R. Sinclair, Siddhartha Banerjee, and Christina Lee Yu.

Sequential Fair Allocation: Achieving the Optimal Envy-Efficiency Tradeoff Curve [arXiv] [video]	Operations Research 2022
Sean R. Sinclair, Gauri Jain, Siddhartha Banerjee, and Christina Lee Yu.
Finalist for the 2022 INFORMS DEI Best Student Paper Award