Distributionally Robust Optimization and Machine Learning for Communication Networks
Speaker: Zhu Han – Houston, TX, United StatesTopic(s): Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing
Abstract
Recently, distributionally robust optimization theory is introduced to overcome the shortcomings of these two approaches, which assumes that the distribution of the random variable is within an ambiguity set. This talk will give a detailed introduction to distributionally robust optimization techniques including the mathematic foundations and their applications in the wireless communication area. First, this talk will briefly explain the decision under uncertainty and the background of the distributionally robust optimization. Second, this talk will explain the concept of uncertainty set and how to choose and build up an uncertainty set based on the statistic learning techniques and historical data samples. Third, this talk will discuss the discrepancy-based distributionally robust optimization approach with Wasserstein distance. Fourth, this talk will discuss the distributionally robust reinforcement learning method which can make the agent more robust when it makes the decision in a high noise environment. In addition, this talk will introduce various communication applications by distributionally robust optimization and distributionally robust machine learning techniques including ultra-reliable communication, age of information minimization in healthcare IoT, computation offloading in space-air-ground integrated networks, etc. Finally, this talk will discuss the conclusions and future work.About this Lecture
Number of Slides: 50Duration: 60 minutes
Languages Available: Chinese (Simplified), English
Last Updated:
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.