Learning and privacy with incomplete data and weak supervision


Montreal, Canada on December 12th @ NIPS'15


Speakers: Wendy Cho, Kamalika Chaudhuri, Nando de Freitas, Max Ott
- with a special issue on the Journal of Privacy and Confidentiality -

Schedule

09.00-09.10  Welcome & Open Remarks
09.10-10.00  Invited Speaker: Kamalika Chaudhuri
10.00-10.30  Posters session & Coffee Break
10.30-11.10  Invited Speaker: Nando de Freitas
11.10-12.10  Papers Session: privacy

  • $(\varepsilon, \delta)$-differential privacy of Gibbs posteriors
    Kentaro Minami, The University of Tokyo
  • Learning with differential privacy: stability, learnability and the sufficiency and necessity of ERM principle
    Yu-Xiang Wang, Carnegie Mellon University
  • Private posterior distributions from variational approximations
    Vishesh Karwa, Carnegie Mellon University

Lunch break – food provided to the attendees

14.30-15.20  Invited Speaker: Wendy Cho
15.20-16.00  Papers Session: weakly-supervised learning

  • Alter-CNN: an approach for learning from label proportions with the application to ice-water Classification
    Fan Li, University of Guelph
  • Message passing for collective graphical models
    Tao Sun, University of Massachusetts Amherst

16.00-16.30  Posters session & Coffee Break
16.30-17.20  Invited Speaker: Max Ott
17.20-18.00  Panel Discussion