32-141
The Power of Multiple Samples in Generative Adversarial Networks
32-141 , United StatesAbstract We bring the tools from Blackwell’s seminal result on comparing two stochastic experiments from 1953, to shine a new light on a modern application of great interest: Generative Adversarial Networks (GAN). Binary hypothesis testing is at the center of training GANs, where a trained neural network (called a critic) determines whether a given sample…
Safe Learning in Robotics
32-141 , United StatesAbstract A great deal of research in recent years has focused on robot learning. In many applications, guarantees that specifications are satisfied throughout the learning process are paramount. For the safety specification, we present a controller synthesis technique based on the computation of reachable sets using optimal control. We show recent results in system decomposition…
Supervisory Control of Discrete Event Systems: A Retrospective and Two Recent Results on Security and Privacy
32-141 , United StatesAbstract Lafortune will begin with a brief retrospective of the theory of supervisory control of discrete event systems, initiated in the seminal work of Ramadge & Wonham over 30 years ago, and compare it with recent work in formal methods in control. He will then present results from his group on two problems: (i) sensor…
Stable Optimal Control and Semicontractive Dynamic Programming
32-141 , United StatesThe LIDS Seminar Series features distinguished speakers in the information and decision sciences who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing.Â
Testing properties of distributions over big domains
32-141 , United StatesThe Stochastics and Statistics Seminar is a weekly meeting organized by the Statistics and Data Science Center (SDSC). It consists of a series of one-hour presentations by worldwide leaders making cutting edge contributions to methodological and theoretical advances in data science. These fields include probability, statistics, optimization, and applied mathematics. The seminar also regularly features…
Recent Methodological Advances in Automated Causal Discovery
32-141 , United StatesIDSS Distinguished Seminars is a monthly lecture series featuring prominent global leaders and academics sharing research in areas that include social networks, causal inference, data privacy, computational social science and other areas that are impacted by the emergence of big data. Â
Data-Driven Models in Power Systems
32-141 , United StatesThe LIDS Seminar Series features distinguished speakers in the information and decision sciences who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing.Â
Geometries of Word Embeddings
32-141 , United StatesThe LIDS Seminar Series features distinguished speakers in the information and decision sciences who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing.Â
A System Level Approach to Controller Synthesis
32-141 , United StatesThe LIDS Seminar Series features distinguished speakers in the information and decision sciences who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing.Â