Events

"Stock or Print? Impact of 3D Printing on Spare Parts Logistics"

Presentation by Professor Jeanette Song
Fuqua School of Business
Duke University

Wednesday, September 26
3:15pm - Refreshments, Lind Hall 305
3:30pm - Graduate Seminar, Lind Hall 305

About:

We present a general framework to study the design of spare parts logistics in the presence of 3D printing technology. We consider multiple parts facing stochastic demands. To minimize long-run average system cost, our model determines which parts to stock and which to print. We derive various structural properties of the problem to gain insights. In some cases, we obtain closed-form optimal solutions; in other cases, we devise efficient algorithms to obtain near optimal solutions. We demonstrate that the optimal printer utilization is in general low, suggesting complementarity between stock and print in cost minimization. (Joint work with Yue Zhang)

Bio:

Jing-Sheng (Jeannette) Song, obtained her Ph.D. from Columbia University, is currently the R. David Thomas Professor and a professor of Operations Management at the Fuqua School of business, Duke University. She studies supply chain management and operations strategy, topics including supply chain inventory planning and disruption management, assemble-to-order systems, global sourcing strategies, and socially responsible operations. Professor Song is an INFORMS Fellow and a Fellow and former President of the Manufacturing and Service Operations Management (MSOM) Society. She serves and has served on the editorial board of several leading academic journals, including Area Editor for Operations Research and Department Editor for IIE Transactions.

"Optimization across ExxonMobil"

Presentation by Alison Cozad
Optimization and Data Analytics
ExxonMobil

Wednesday, September 19
3:15pm - Refreshments, Lind Hall 305
3:30pm - Graduate Seminar, Lind Hall 305

About:

A large, global company like ExxonMobil offers a rich set of challenging optimization problems, from process design to circuit supply planning to ship routing. In this seminar, we will discuss the optimization scope at ExxonMobil and a few recent projects. We will focus on the learnings I’ve had since entering industry, while comparing these elements to academia. My goal is to give an understanding of key skills unique to an industrial optimizer and a flavor of the optimization problems at ExxonMobil.

Bio:

Alison Cozad works in Optimization and Data Analytics at ExxonMobil. She has led and contributed to projects in real-time optimization, optimization solution analysis, production planning, and data analytics in the crude characterization space. Prior to ExxonMobil, she received her PhD from Carnegie Mellon and her bachelor’s from the University of Minnesota, both in chemical engineering. Her thesis work with Dr. Nick Sahinidis focused on the intersection of optimization and machine learning. There, she developed the ALAMO package, for the Automatic Learning of Algebraic Models. Alison is enthusiastically Minnesotan. She grew up in Burnsville, MN where she learned a love of Juicy Lucys and Duck, Duck, Grey Duck. She makes sure to head to Bemidji every January for a cold weekend of Norwegian Camp.

"Spatial Pricing in Ride-Sharing Networks"

Presentation by Professor Kostas Bimpikis
Operations, Information and Technology
Graduate School of Business
Stanford University

Wednesday, September 12
3:15pm - Refreshments, Lind Hall 305
3:30pm - Graduate Seminar, Lind Hall 305

About:

We explore spatial price discrimination in the context of a ride-sharing platform that serves a network of locations. Riders are heterogeneous in terms of their destination preferences and their willingness to pay for receiving service. Drivers decide whether, when, and where to provide service so as to maximize their expected earnings, given the platform’s prices. Our findings highlight the impact of the demand pattern on the platform’s prices, profits, and the induced consumer surplus. In particular, we establish that profits and consumer surplus are maximized when the demand pattern is "balanced" across the network’s locations. In addition, we show that they both increase monotonically with the balancedness of the demand pattern (as formalized by its structural properties). Furthermore, if the demand pattern is not balanced, the platform can benefit substantially from pricing rides differently depending on the location they originate from. Finally, we consider a number of alternative pricing and compensation schemes that are commonly used in practice and explore their performance for the platform. (joint work with Ozan Candogan and Daniela Saban)

Bio:

Kostas Bimpikis is an Associate Professor of Operations, Information and Technology at Stanford University’s Graduate School of Business. Prior to joining Stanford, he spent a year as a postdoctoral research fellow at the Microsoft Research New England Lab. Professor Bimpikis has received a PhD in Operations Research from the Massachusetts Institute of Technology in 2010, an MS in Computer Science from the University of California, San Diego and a BS degree in Electrical and Computer Engineering from the National Technical University of Athens, Greece. Professor Bimpikis' research agenda lies in the interface of operations, economics and information technology. Much of his current research is focused on studying the economics of complex social networks and identifying the implications for individuals and businesses. Moreover, he is interested in issues arising in the operations of Internet-based markets.

"Distributed Non-Convex First-Order Optimization and Information Processing: Lower Complexity Bounds and Rate Optimal Algorithms"

Presentation by Professor Mingyi Hong
Department of Electrical and Computer Engineering
University of Minnesota—Twin Cities

Wednesday, September 5
3:15pm - Refreshments, Lind Hall 305
3:30pm - Graduate Seminar, Lind Hall 305

About:

We consider a class of distributed non-convex optimization problems, in which a number of agents are connected by a network, and they collectively optimize a sum of smooth (possibly non-convex) local objective functions. We address the following general question: What is the fastest rate that any distributed algorithms can achieve (to compute first-order stationary solution), and how to achieve those rates. To address this question, we consider a class of unconstrained non-convex problems, and allow the agents to access local (first-order) gradient information. We develop a lower bound analysis that identifies difficult problem instances for any first-order method. We show that in the worst-case it takes any first-order algorithm O(D/epsilon) iterations to achieve certain epsilon-solution, where D is the network diameter. Further, we develop one of the first rate-optimal distributed method whose rate precisely matches the lower bound (up to a ploylog factor). The algorithm combines ideas from distributed consensus, nonlinear optimization, as well as classical fast solvers for linear systems. Extension on how to compute high-order stationary solutions will also be discussed.

Bio:

Mingyi Hong received his Ph.D. degree from University of Virginia in 2011. Since August 2017, he has been an Assistant Professor in the Department of Electrical and Computer Engineering, University of Minnesota. From 2014-2017 he has been an Assistant Professor with the Department of Industrial and Manufacturing Systems Engineering, Iowa State University. He is serving on the IEEE Signal Processing for Communications and Networking (SPCOM), and Machine Learning for Signal Processing (MLSP) Technical Committees. He has coauthored works that have been selected as finalists for the Best Paper Prize for Young Researchers in Continuous Optimization in 2013, 2016. His research interests are primarily in optimization theory and applications in signal processing and machine learning.

"Models to Operate and Evaluate Mobility-as-a-Service"

Presentation by Professor Joseph Y. J. Chow
Department of Civil and Urban Engineering
Deputy Director, C²SMART University Transportation Center
New York University

About:

Recent advances in technology have brought about a renaissance in new mobility paradigms along with their own sets of growing pains, whether it’s carsharing (e.g. Car2Go in San Diego), microtransit (e.g. Kutsuplus in Helsinki), or shared autonomous vehicle fleets. The need to make use of customer and vehicle real time information in dynamic decision-making for these “mobility as a service” models is greater than ever before. Dynamic decision-making, particularly in a network context, has a number of challenges. Two areas are: 1) learning models that adequately describe the full customer behavioral responses in scheduling trips throughout the day; and 2) designing dynamic policies such as where to position idle vehicles or whether to switch operational mode over time. Theoretical overview of models to address these challenges, along with a discussion of computational experiments, will be presented.

Bio:

Joseph Chow is an Assistant Professor in the Department of Civil & Urban Engineering and the Deputy Director at the C2SMART Tier-1 University Transportation Center at NYU, and heads BUILT@NYU: the Behavioral Urban Informatics, Logistics, and Transport Laboratory. He is an NSF CAREER award recipient; he serves as the incoming Chair of the Urban Transportation SIG at INFORMS Transportation Science & Logistics Society, and is an appointed member of the Editorial Boards for Transportation Research Part B and the Committee on Transportation Network Modeling (ADB30) at the Transportation Research Board of the National Academies. At NYU he is an Associated Faculty at CUSP and Rudin Center. Prior to NYU, Dr. Chow was the Canada Research Chair at Ryerson University. Chow has over 80 publications to date, of which over 40 are in top journals in the transportation field. He has a Ph.D. in Civil Engineering from UC Irvine (‘10), and an M.Eng. (‘01) and B.S. (‘00) in Civil Engineering from Cornell University with a minor in Applied Math.