Inside Our Program

Program Events

Events

• Feb

  3

  IEMS Seminar 02/03 Kibaek Kim Winter 2026

  Department of Industrial Engineering and Management Sciences (IEMS)

  11:00 AM A230, Technological Institute

  EVENT DETAILSmore info

  Title: Privacy-Preserving Federated Learning at Scale: From Algorithms to Supercomputers

  Bio: I am a Computational Mathematician in Laboratory for Applied Mathematics, Numerical Software, and Statistics, Mathematics and Computer Science Division at Argonne National Laboratory, and a Senior Scientist at-Large at the University of Chicago Consortium for Advanced Science and Engineering. My research focuses on federated learning algorithms and software development, as well as modeling and numerical algorithms for large-scale optimization on high-performance computing systems and GPUs. My work is applied to areas including electric grid systems, healthcare, and key scientific domains of interest to the Department of Energy. Before joining Argonne, I obtained a Ph.D. degree in Industrial Engineering and Management Sciences from Northwestern University. I am a recipient of DOE Early Career Research Program award. I serve as associate editors in Mathematical Programming Computation and Naval Research Logistics and board members for COIN-OR Foundation and IISE Energy Systems.

  Abstract: Federated learning (FL) is increasingly attractive for AI for Science because it enables collaborative model training across institutions and facilities without centralizing sensitive data. In this talk, I will give a brief overview of our DOE-funded AI for Science effort and the multidisciplinary team building scalable learning workflows for scientific and energy applications. I will then introduce privacy-preserving federated learning, focusing on practical mechanisms (e.g., secure aggregation and differential privacy) and the core tradeoffs they impose on accuracy, communication, and systems performance.

        The second half of the talk will focus on our recent queue-aware FL protocol designed for cross-facility training on leadership-class HPC systems. Unlike conventional synchronous or fully asynchronous FL, our algorithm treats batch-scheduler delays as a first-class systems signal: it adapts local work and aggregation to time-varying queue and execution delays to reduce straggler effects while controlling staleness. I will present the key ideas and empirical results from deploying FL across Aurora, Frontier, Polaris, and Perlmutter, highlighting end-to-end performance, stability under heterogeneous runtimes, and what this implies for building reliable, privacy-preserving, multi-site AI training pipelines for science.

  more less

  TIME Tuesday, February 3, 2026 at 11:00 AM - 12:00 PM

  LOCATION A230, Technological Institute    map it

  ADD TO CALENDAR

  CONTACT Kendall Minta    kendall.minta@gmail.com EMAIL

  CALENDAR Department of Industrial Engineering and Management Sciences (IEMS)

• Apr

  7

  IEMS Wasserstrom Lecture - Jim Dai April 7

  Department of Industrial Engineering and Management Sciences (IEMS)

  11:00 AM Suite 1400, Krebs Classroom, North Campus Parking Garage

  EVENT DETAILSmore info

  IEMS Distinguished Lecturer Prof Jim Dai

  more less

  TIME Tuesday, April 7, 2026 at 11:00 AM - 12:00 PM

  LOCATION Suite 1400, Krebs Classroom, North Campus Parking Garage    map it

  ADD TO CALENDAR

  CONTACT Kendall Minta    kendall.minta@gmail.com EMAIL

  CALENDAR Department of Industrial Engineering and Management Sciences (IEMS)

• Apr

  7

  MLDS Bias Talks: Differential Privacy

  Master of Science in Machine Learning and Data Science (MLDS)

  5:30 PM M152, Technological Institute

  EVENT DETAILS

  This lecture introduces Differential Privacy (DP) as a mathematically rigorous framework for privacy-preserving data analysis, motivated by the well-documented failures of traditional anonymization approaches such as linkage attacks and the mosaic effect. The lecture covers the formal definition of DP, key properties including the privacy budget (ε), and the mechanisms used to achieve it — Laplace, Exponential, and Gaussian — alongside practical considerations around the privacy-utility tradeoff. Real-world deployments at organizations are examined, with a forward-looking discussion of the emerging challenges of applying DP to large language model training.

  more less

  TIME Tuesday, April 7, 2026 at 5:30 PM - 6:30 PM

  LOCATION M152, Technological Institute    map it

  ADD TO CALENDAR

  CONTACT Master of Science in Machine Learning and Data Science Program    mlds@northwestern.edu EMAIL

  CALENDAR Master of Science in Machine Learning and Data Science (MLDS)

• Apr

  8

  MLDS Bias Talks: Data Anonymization

  Master of Science in Machine Learning and Data Science (MLDS)

  12:00 PM McCormick Education Center, Room 1400 (Krebs), North Campus Parking Garage

  EVENT DETAILS

  This lecture introduces data anonymization as a formal approach to protecting individual privacy when releasing datasets, motivating the need for rigorous guarantees through the well-known failures of naive de-identification such as linkage attacks and quasi-identifier re-identification. The lecture covers core Statistical Disclosure Control (SDC) concepts and a range of anonymization techniques including generalization, suppression, pseudonymization, and data perturbation. Practical methodology for applying anonymization in context-specific settings is presented with attention to the inherent privacy-utility tradeoff that practitioners must navigate.

  more less

  TIME Wednesday, April 8, 2026 at 12:00 PM - 1:00 PM

  LOCATION McCormick Education Center, Room 1400 (Krebs), North Campus Parking Garage    map it

  ADD TO CALENDAR

  CONTACT Master of Science in Machine Learning and Data Science Program    mlds@northwestern.edu EMAIL

  CALENDAR Master of Science in Machine Learning and Data Science (MLDS)

• Apr

  9

  MLDS Bias Talks: Homomorphic Encryption

  Master of Science in Machine Learning and Data Science (MLDS)

  5:30 PM M152, Technological Institute

  EVENT DETAILS

  This lecture introduces Homomorphic Encryption (HE), a powerful cryptographic technique that enables computations to be performed directly on encrypted data without requiring access to a secret key, such that the decrypted result is identical to what would be obtained from computing on the original plaintext. The session covers the core concepts and mathematical foundations of HE, including additive and multiplicative homomorphism, the role of noise in fully homomorphic schemes, and practical tools such as Microsoft SEAL and HELib. Applications spanning healthcare, finance, machine learning, and cloud computing are examined alongside the key deployment challenge of computational overhead.

  more less

  TIME Thursday, April 9, 2026 at 5:30 PM - 6:30 PM

  LOCATION M152, Technological Institute    map it

  ADD TO CALENDAR

  CONTACT Master of Science in Machine Learning and Data Science Program    mlds@northwestern.edu EMAIL

  CALENDAR Master of Science in Machine Learning and Data Science (MLDS)

• Apr

  21

  IEMS Seminar Series - April 21 - Zhengyuan Zhou

  Department of Industrial Engineering and Management Sciences (IEMS)

  11:00 AM

  EVENT DETAILS

  IEMS Weekly Seminar Series

  more less

  TIME Tuesday, April 21, 2026 at 11:00 AM - 12:00 PM

  ADD TO CALENDAR

  CONTACT Kendall Minta    kendall.minta@gmail.com EMAIL

  CALENDAR Department of Industrial Engineering and Management Sciences (IEMS)

• Apr

  28

  IEMS Undergrad Seminar - Jim Roth - April 28

  Department of Industrial Engineering and Management Sciences (IEMS)

  11:00 AM Suite 1400, Krebs Classroom, North Campus Parking Garage

  EVENT DETAILS

  IEMS Undergrad Seminar - April 28

  more less

  TIME Tuesday, April 28, 2026 at 11:00 AM - 12:00 PM

  LOCATION Suite 1400, Krebs Classroom, North Campus Parking Garage    map it

  ADD TO CALENDAR

  CONTACT Kendall Minta    kendall.minta@gmail.com EMAIL

  CALENDAR Department of Industrial Engineering and Management Sciences (IEMS)