BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Algorithmic Foundations of Differential Privacy (Chapters 1 an
 d 2) - James Bell\, University of Cambridge
DTSTART:20181121T170000Z
DTEND:20181121T190000Z
UID:TALK115168@talks.cam.ac.uk
CONTACT:Adrià Garriga Alonso
DESCRIPTION:Link: http://www.cis.upenn.edu/~aaroth/privacybook.html (DO NO
 T MINDLESSLY PRINT\, we will only be going over a tenth (Chapters 1 and 2)
  of this document so you don't need to print the rest unless you are extra
 ordinarily keen)\n\nAbstract: "A major imminent concern in the deployment 
 of AI and the collection of data regards the privacy implications. In this
  week's reading group we will learn the definition of Differential Privacy
 \, why it is useful\, what it is/guarantees\, what it isn't/doesn't and a 
 little about how much is and is not possible within the constraint that it
  provides.\n\nThe problem of privacy-preserving data analysis has a long h
 istory spanning multiple disciplines. As electronic data about individuals
  becomes increasingly detailed\, and as technology enables ever more power
 ful collection and curation of these data\, the need increases for a robus
 t\, meaningful\, and mathematically rigorous definition of privacy\, toget
 her with a computationally rich class of algorithms that satisfy this defi
 nition. Differential Privacy is such a definition."\n\n--\n\nAt 17:00\, we
  will start reading the paper\, mostly individually. At 17:30\, the discus
 sion leader will start going through the paper\, making sure everyone unde
 rstands\, and encouraging discussion about its contents and implications.\
 n\nEven if you think you cannot contribute to the conversation\, you shoul
 d give it a try. Last year we had several people from non-computer-y backg
 rounds\, and others who hadn't thought about alignment before\, that ended
  up being essential. If you have already read the paper in your own time y
 ou can come in time for the discussion.\n\nA basic understanding of machin
 e learning is helpful\, but detailed knowledge of the latest techniques is
  not required. Each session will have a brief recap of immediate necessary
  knowledge. The goal of this series is to get people to know more about th
 e existing work in AI research\, and eventually contribute to the field.\n
 \nInvite your friends to join the talks.cam page (https://talks.cam.ac.uk/
 show/index/80932) or the Facebook group (https://www.facebook.com/groups/1
 070763633063871). Details about the next meeting\, the week's topic and ot
 her events will be advertised in these places as well.
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38
END:VEVENT
END:VCALENDAR