A (Con)Sequential View of Information for Statistical Learning and Optimization
Speaker: Tara Javidi
Jacobs Family Scholar and Professor
Electrical and Computer Engineering
UCSD
Abstract: In most communication systems, adapting transmission strategies to the (unpredictable) realization of channel output at the receiver requires an (unrealistic) assumption about the availability of a reliable “feedback” channel. This unfortunate fact, combined by the historical linkage between teaching information theory and digital communication curriculum has kept “feedback information theory” less taught, discussed, appreciated and understood compared to other topics in our field.
This talk, in contrast, highlights important and challenging problems in machine learning, optimization, statistics, and control theory, where the problem of acquiring information in an adaptive manner arises very naturally. Thus, I will argue that an increased emphasis on (teaching) feedback information theory can provide vast and exciting research opportunities at the intersection of information theory and these fields. In particular, I will revisit simple-to-teach results in feedback information theory including sequential hypothesis testing, arithmetic coding, successive refinement, noisy binary search, and posterior matching. Drawing on my own research, I will also highlight the successful application of these sequential techniques in a variety of problem instances such as black-box optimization, distribution estimation, and active machine learning with imperfect labels.
Speaker bio: Tara Javidi received her BS in electrical engineering at Sharif University of Technology, Tehran, Iran. She received her MS degrees in electrical engineering (systems) and in applied mathematics (stochastic analysis) from the University of Michigan, Ann Arbor as well as her Ph.D. in electrical engineering and computer science in 2002. She is currently a Jacobs Family Scholar and Professor of Electrical and Computer Engineering and a founding co-director of the Center for Machine-Intelligence, Computing and Security (MICS) at UCSD.
Tara Javidi’s research interests are in theory of active learning, information acquisition and statistical inference, information theory with feedback, stochastic control theory, and wireless networks.
Location: In-person at YINS, 17 Hillhouse Ave, 3rd floor. Yale-only livestream: https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=accec6b8-cece-4306-869b-afce0158dceb
Lunch will be served.
