Advising

I have been fortunate to work with a number of exceptional students. I greatly enjoy working with students and view this work as a highly collaborative process that allows us both to solve problems on the cutting edge of research. This page describes some of my Ph.D. students and their placement (a complete list can be found in my CV).

Jiaqi Zhou (2021). "Essays in stochastic modeling and optimization." First position: Citibank.

Jiaqi's dissertation considered two different classes of stochastic models. Her first paper used queueing analysis to characterize the equilibrium behavior of customers in a service system that offers a choice between free, but slow service and a faster version that charges a fee. Each customer observes the load on both the free and paid queues at the moment of arrival; thus, the arrival rate of each queue varies dynamically over time. Jiaqi's second paper dealt with the problem of optimally allocating a simulation budget in a situation where there are uncountably many design alternatives. An interesting theoretical insight of this work was that, rather than assigning the budget to these alternatives, one can instead divide it between the elements of a basis for the design space.

  • Zhou, J. & Ryzhov, I.O. (2021) "Equilibrium analysis of observable express service with customer choice." Queueing Systems 99(3-4), 243-281.

Ye Chen (2018). "Stochastic optimization: approximate Bayesian inference and complete expected improvement." First position: Assistant Professor, Statistical Sciences and Operations Research, Virginia Commonwealth University.

Ye's dissertation solved two open problems in optimal learning. In the theoretical analysis of learning algorithms, the state of the art is to use large deviations theory to characterize optimal budget allocations. Ye made a connection between this theory and a simple, recently introduced myopic Bayesian procedure called "complete expected improvement," showing that this algorithm can learn the rate-optimal allocation without any tuning. In another line of work, Ye studied approximate Bayesian inference methods, which are used to learn in the presence of incomplete or censored information, and proved that a wide variety of these methods is consistent (recovers the true parameter values in the underlying model). This was the first rigorous theoretical support for a class of procedures that had been known to perform well in a wide variety of applications, some of them dating back to 1990.

Ye was a finalist in the 2016 Best Theoretical Paper award competition at the Winter Simulation Conference.

  • Chen, Y. & Ryzhov, I.O. (2020) "Consistency analysis of sequential learning under approximate Bayesian inference." Operations Research 68(1), 295-307.

  • Chen, Y. & Ryzhov, I.O. (2019) "Complete expected improvement converges to an optimal budget allocation." Advances in Applied Probability 51(1), 209-235.

Bin Han (2015). "Statistical and optimal learning with applications in business analytics." First position: Blackrock, Inc.

Bin's dissertation focused on both statistical and optimal learning, mainly in the context of non-profit management. We first worked on an empirical project in which we applied model selection methods to a massive dataset covering over 8 million recorded direct-mail interactions with donors to the American Red Cross (ARC). The results of this study, which were presented to ARC marketing executives and later published in Management Science, identified fundraising design practices that exerted a positive impact on response rates. In his second paper, Bin explored the closely related problem of optimizing future fundraisers based on the regression model trained from the data.

Bin won numerous awards for his work. Within the University of Maryland, he won the prestigious Ann G. Wylie Dissertation Fellowship (a full-semester scholarship), as well as the Phi Delta Gamma Graduate Fellowship. He was also recognized as a finalist in the 2015 INFORMS Washington DC Chapter Student Excellence Award competition.

  • Han, B., Ryzhov, I.O. & Defourny, B. (2016) "Optimal learning in linear regression with combinatorial feature selection." INFORMS Journal on Computing 28(4), 721-735.

  • Ryzhov, I.O., Han, B. & Bradić, J. (2016) "Cultivating disaster donors using data analytics." Management Science 62(3), 849-866.

Zi Ding (2014). "Optimal learning with non-Gaussian rewards." First position: Citadel, LLC

Zi studied the theoretical problem of information collection in a setting where the observed rewards are non-Gaussian. In the Gaussian case, one approach for calculating the optimal "Gittins index" policy is to construct a continuous-time Brownian motion whose increments have the same distribution as the rewards in the original discrete-time problem. Zi found that, for some non-Gaussian reward distributions, it is possible to conduct a similar analysis using a more general Lévy process model. His work provides the first theoretical characterization of the optimal policy in this continuous-time setting.

Zi's dissertation paper placed as a finalist in the 2014 INFORMS Junior Faculty Forum paper competition.

  • Ding, Z. & Ryzhov, I.O. (2016) "Optimal learning with non-Gaussian rewards." Advances in Applied Probability 48(1), 112-136.

Huashuai Qu (2014). "Simulation optimization: new approaches and an application." First position: Google, Inc.

Huashuai made several contributions to simulation optimization methodology (some of them with Prof. Michael Fu). He worked with me on the problem of learning unknown correlation structures, where we are trying to learn about a large number of competing design alternatives subject to a small simulation budget. Huashuai used approximate Bayesian inference to develop a tractable statistical model that could identify and exploit similarities and differences between alternatives based on experiments with individual alternatives (several years later, Ye Chen developed the theory behind this approach further). Huashuai also worked with me on a consulting project for Vendavo, Inc., in which approximate Bayesian inference was used to learn demand curves in B2B pricing.

Huashuai's work won the 2012 INFORMS Computing Society Student Paper Award, as well as the Best Theoretical Paper Award at the 2012 Winter Simulation Conference.

  • Qu, H. Ryzhov, I.O., Fu, M.C., Bergerson, E., Kurka, M. & Kopacek, L. (2020) "Learning demand curves in B2B pricing: a new framework and case study." Production and Operations Management 29(5), 1287-1306.

  • Qu, H., Ryzhov, I.O., Fu, M.C. & Ding, Z. (2015) "Sequential selection with unknown correlation structures." Operations Research 63(4), 931-948.