BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:0-5067@eng.ufl.edu
DTSTART;TZID=America/New_York:20220823T124500
DTEND;TZID=America/New_York:20220823T134500
DTSTAMP:20220726T164949Z
URL:https://www.eng.ufl.edu/news-events/events/tp-seminar-privacy-in-feedb
 ack-decision-systems/
SUMMARY:T&amp\;P Seminar - Privacy in Feedback Decision Systems
DESCRIPTION:Privacy in Feedback Decision Systems\nTuesday\, August 23\, 202
 2\, at 12:50 pm\nLocation: MAE-A 303\nDr. Matt Hale\nAssistant Professor\n
 Department of Mechanical &amp\; Aerospace Engineering\nUniversity of Flori
 da\nAbstract\nEngineering systems are gathering more data than ever. In ap
 plications ranging from smart power grids to traffic systems to connected 
 homes\, data is increasingly used to drive feedback loops for the control 
 of such systems or for learning in them. Often this data is user data in t
 he sense that it belongs to an end user or provides information about them
 \, and increasingly this user data is sensitive. For example\, the locatio
 n of a user's vehicle throughout the day can reveal their activities\, clo
 se relationships\, and places of work and residence. What emerges is a nee
 d to simultaneously safeguard sensitive data (for the benefit of users) an
 d preserve that data's usefulness in decision systems\, namely those used 
 in control and learning. In this talk\, I will present recent work from my
  group that helps address this need by developing new privatization strate
 gies for a class of symbolic systems\, namely Markov chains\, which are us
 ed in a wide variety of engineering applications. This work has made the f
 irst connections between symbolic systems and a formal privacy framework c
 alled "differential privacy\," and this talk will cover the novel\, mathem
 atically rigorous privacy protections that we have developed\, along with 
 formal guarantees that privatized data remains useful in feedback decision
  systems. I will also go over recent developments that bring privacy to se
 veral widely used control setups\, including linear-quadratic control and 
 multi-agent control.\nBiography\nMatthew Hale is an Assistant Professor of
  Mechanical and Aerospace Engineering at the University of Florida. He rec
 eived his BSE in Electrical Engineering summa cum laude from the Universit
 y of Pennsylvania in 2012 and his MS and Ph.D. in Electrical and Computer 
 Engineering from the Georgia Institute of Technology in 2015 and 2017\, re
 spectively. His research interests include multi-agent systems\, mobile ro
 botics\, privacy in control\, artificial intelligence\, and distributed op
 timization. He received an NSF CAREER Award in 2020\, an ONR YIP in 2022\,
  and a 2022 Excellence Award for Assistant Professors from the University 
 of Florida (for being one of the top 10 assistant professors across all co
 lleges on campus).\nMAE Faculty Host: Carl Crane
CATEGORIES:Seminars
LOCATION:MAE-A Room 303\, 939 Sweetwater Drive\, Gainesville\, FL\, 32611\,
  United States
GEO:29.643814;-82.34865
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=939 Sweetwater Drive\, Gain
 esville\, FL\, 32611\, United States;X-APPLE-RADIUS=100;X-TITLE=MAE-A Room
  303:geo:29.643814,-82.34865
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
DTSTART:20220313T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR