News & EventsDepartment Events
Events
-
Nov5
EVENT DETAILS
Abstract: Advances in computational power and AI have increased interest in reinforcement/supervised learning approaches to inventory management. This paper provides a theoretical foundation for these approaches and investigates the benefits of restricting to policy structures that are well-established by decades of inventory theory. In particular, we prove generalization guarantees for learning several well-known classes of inventory policies, including base-stock and (s, S) policies, by leveraging the celebrated Vapnik-Chervonenkis (VC) theory. We apply the concepts of the Pseudo-dimension and Fat-shattering dimension from VC theory to determine the generalization error of inventory policies, that is, the difference between an inventory policy's performance on training data and its expected performance on unseen data. We focus on a classical setting without contexts, but allow for an arbitrary distribution over demand sequences and do not make any assumptions such as independence over time. We corroborate our supervised learning results using numerical simulations.
Managerially, our theory and simulations translate to the following insights. First, there is a principle of "learning less is more" in inventory management: depending on the amount of data available, it may be beneficial to restrict oneself to a simpler, albeit suboptimal, class of inventory policies to minimize overfitting errors. Second, the number of parameters in a policy class may not be the correct measure of overfitting error: in fact, the class of policies defined by T time-varying base-stock levels exhibits a generalization error an order of magnitude lower than that of the two-parameter (s, S) policy class. Finally, our research suggests situations in which it could be beneficial to incorporate the concepts of base-stock and inventory position into black-box learning machines, instead of having these machines directly learn the order quantity actions.
This is joint work with Yaqi Xie (Chicago Booth 3-Year PhD Student) and Will Ma (Columbia Business School). Link to the paper: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4794903
Bio:
Linwei Xin is an associate professor of operations management at the University of Chicago Booth School of Business. He specializes in inventory and supply chain management, where he designs cutting-edge models and algorithms that enable organizations to effectively balance supply and demand in various contexts with uncertainty.
Xin's research using asymptotic analysis to study stochastic inventory theory is renowned and has been recognized with several prestigious INFORMS paper competition awards, including First Place in the George E. Nicholson Student Paper Competition in 2015 and the Applied Probability Society Best Publication Award in 2019. Xin's recent interest focuses on AI for supply chains, driven by labor shortages, reshoring trends, global supply chain disruptions, and e-commerce growth. He leverages various tools such as neural networks, VC theory, applied probability, online optimization/learning, and random graph theory to address emerging challenges arising from AI-driven automation. His work targets problems in inventory management, robotics and automation in modern warehousing, dual-sourcing, real-time order fulfillment, omnichannel, and transportation network design. His research on implementing state-of-the-art multi-agent deep reinforcement learning techniques in Alibaba's inventory replenishment system was selected as a finalist for the INFORMS 2022 Daniel H. Wagner Prize, with over 65% algorithm-adoption rate within Alibaba's own supermarket brand Tmall Mart. His research on designing dispatching algorithms for robots in JD.com's intelligent warehouses was recognized as a finalist for the INFORMS 2021 Franz Edelman Award, with estimated annual savings in the hundreds of millions of dollars.
Xin currently serves as an associate editor for Operations Research, Management Science, Manufacturing & Service Operations Management, and Naval Research Logistics.
TIME Tuesday, November 5, 2024 at 11:00 AM - 12:00 PM
LOCATION A230, Technological Institute map it
CONTACT Kendall Minta kendall.minta@gmail.com EMAIL
CALENDAR Department of Industrial Engineering and Management Sciences (IEMS)
-
Nov7
EVENT DETAILS
Abstract:
While the typical behaviors of stochastic systems are often deceptively oblivious to the tail distributions of the underlying uncertainties, the ways rare events arise are vastly different depending on whether the underlying tail distributions are light-tailed or heavy-tailed. In light-tailed settings, a system-wide rare event arises because every component of the system subtly deviates from its nominal behavior as if the entire system has conspired to provoke the rare event (conspiracy principle), whereas, in heavy-tailed settings, a system-wide rare event arises because a small number of components fail catastrophically (catastrophe principle). In the first part of this talk, I will introduce the recent developments in the theory of large deviations for heavy-tailed stochastic processes at the sample path level and rigorously characterize the catastrophe principle for such processes.
The empirical success of deep learning is often attributed to the mysterious ability of stochastic gradient descents (SGDs) to avoid sharp local minima in the loss landscape, as sharp minima are believed to lead to poor generalization. To unravel this mystery and potentially further enhance such capability of SGDs, it is imperative to go beyond the traditional local convergence analysis and obtain a comprehensive understanding of SGDs' global dynamics in complex non-convex loss landscapes. In the second part of this talk, I will characterize the global dynamics of SGDs building on the heavy-tailed large deviations and local stability framework developed in the first part. This leads to heavy-tailed counterparts of the classical Freidlin-Wentzell and Eyring-Kramers theories. Moreover, we reveal a fascinating phenomenon in deep learning: by injecting and then truncating heavy-tailed noises during the training phase, SGD can almost completely avoid sharp minima, resulting in improved generalization performance for test data.
Bio:
Chang-Han Rhee is an Assistant Professor in Industrial Engineering and Management Sciences at Northwestern University. Before joining Northwestern University, he was a postdoctoral researcher at Centrum Wiskunde & Informatica and Georgia Tech. He received his Ph.D. from Stanford University. His research interests include applied probability, stochastic simulation, experimental design, and the theoretical foundation of machine learning. His research has been recognized with the 2016 INFORMS Simulation Society Outstanding Publication Award, the 2012 Winter Simulation Conference Best Student Paper Award, the 2023 INFORMS George Nicholson Student Paper Competition (2nd place), and the 2013 INFORMS George Nicholson Student Paper Competition (finalist). Since 2022, his research has been supported by the NSF CAREER Award.
TIME Thursday, November 7, 2024 at 11:00 AM - 12:00 PM
LOCATION A230, Technological Institute map it
CONTACT Kendall Minta kendall.minta@gmail.com EMAIL
CALENDAR Department of Industrial Engineering and Management Sciences (IEMS)
-
Nov19
EVENT DETAILS
Talk abstract: Benders decomposition is a mathematical decomposition technique designed to solve large-scale linear and mixed-integer programs. Since its introduction in 1962, the approach has been successfully applied to a wide variety of problems arising in supply chain management, transportation, telecommunications, and energy management. Despite its success, however, it has long been overshadowed by dual decomposition methods such as Lagrangian relaxation and Dantzig-Wolfe decomposition. Over the last two decades, one has witnessed a renewed interest in Benders decomposition with the introduction of several novel ideas to improve performance. The purpose of this talk is to give an overview of the main acceleration techniques by focusing on two families of problems where Benders decomposition has proven especially effective: facility location problems and network design problems. After briefly explaining the general methodology and practical enhancements, we will present examples of successful applications to set covering problems and fixed-charge network design problems. In each case, we will focus on strategies for generating strong cuts efficiently, including the application of unified cut generation frameworks and the use of normalization constraints in the dual subproblem.
Bio: Jean-François Cordeau obtained his Ph.D. in Applied Mathematics at École Polytechnique de Montréal in 1999. He is a professor of Operations Management at HEC Montréal, where he also holds the Chair in Logistics and Transportation. He has authored or co-authored more than 175 scientific articles in combinatorial optimization and mathematical programming, focusing primarily on vehicle routing and logistics network design. He has also supervised more than 75 M.Sc. and Ph.D. students. Dr. Cordeau is an Area Editor of Transportation Science and a member of the Editorial Board of Computers & Operations Research. He has worked as a consultant for several Canadian and European organizations in the private and public sectors. He is currently one of the scientific directors of IVADO Labs. He received the Canadian Operational Research Society (CORS) Award of Merit in 2016 and the Pierre-Laurin Award for Research Excellence at HEC Montréal in 2018. In 2023, he and ten of his colleagues won the CORS Practice Prize for their work on maritime vessel routing.
TIME Tuesday, November 19, 2024 at 11:00 AM - 12:00 PM
LOCATION Hive Annex, Ford Motor Company Engineering Design Center map it
CONTACT Kendall Minta kendall.minta@gmail.com EMAIL
CALENDAR Department of Industrial Engineering and Management Sciences (IEMS)
-
Dec7
EVENT DETAILS
Fall classes end
TIME Saturday, December 7, 2024
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Dec14
EVENT DETAILS
The ceremony will take place on Saturday, December 14 in Pick-Staiger Concert Hall, 50 Arts Circle Drive.
*No tickets required
TIME Saturday, December 14, 2024 at 4:00 PM - 6:00 PM
LOCATION Pick-Staiger Concert Hall map it
CONTACT Andi Joppie andi.joppie@northwestern.edu EMAIL
CALENDAR McCormick School of Engineering and Applied Science