Date: Thursday, Feb 8, 2024
Time: Noon – 1:00 pm
Location: 9th floor Atrium in Coda Building (756 W Peachtree St NW, Atlanta, GA 30308)
Also live streamed at: https://gatech.zoom.us/j/99381428980
Speaker: Sherief Reda
Using Machine Learning for Combinatorial Optimization (ML4CO): Case Studies and Research Directions
Abstract: Combinatorial optimization (CO) methods are routinely used in many scientific fields to identify optimal solutions among a large but finite set of possible solutions for problems of interests. Given the recent success of machine learning (ML) techniques in classification of natural signals (e.g., voice, image, text), it is natural to ask how machine learning methods can be used to improve the quality of solution or the runtime of combinatorial optimization algorithms? In this talk I will provide a general taxonomy and research directions for the use of machine learning techniques in combinatorial optimization. Through a series of case studies drawn from both academic research and industry applications, the tangible advantages of incorporating ML into CO processes will be demonstrated. These examples span diverse areas, including transportation logistics planning, integer linear programming solvers, and optimization of digital circuit design. The talk will conclude with an outline of a number of challenges for future research.
Bio: Sherief Reda is a professor at the School of Engineering and Computer Science Department at Brown University. He is co-author of over 150 publications in the areas of energy-efficient computing, electronic design automation and combinatorial optimization. He has been a PI or co-PI on more than $22M of funded projects from federal agencies and industry corporations. He received the NSF CAREER award in 2009, and he is a Fellow of IEEE. Besides his academic work, Reda worked as a Principal Scientist at Amazon’s Supply Chain and Optimization Technology team during 2021-2023 while on leave from Brown, and he currently serves as an Amazon Scholar.
Note(s):