Home
Portal
Grstats
Latest images
Register
Log in
grstats- Posts : 966
Join date : 2009-10-21 
1st Research Seminar of the AUEB School of Information Sciences & Technology by Ioannis Tsitsiklis
Tue 12 Mar 2019 - 14:48
1st Research Seminar of the School of Information Sciences & Technology, March, 2019
Ioannis Tsitsiklis
Massachusetts Institute of Technology
Safeguarding Privacy in Dynamic Decision-Making Problems
FRIDAY 15/3/2019
11:00 – 12:00
ROOM Τ102, 1st FLOOR,
NEW AUEB BUILDING (TRIAS 2)
ABSTRACT
The increasing ubiquity of large-scale infrastructures for surveillance and data analysis has made understanding the impact of privacy a pressing priority in many domains. We propose a framework for studying a fundamental cost vs. privacy tradeoff in dynamic decision-making problems. The central question is: how can a decision maker take actions that are efficient for her goal, while simultaneously ensuring these actions do not inadvertently reveal her private information, even when observed and analyzed by a powerful adversary? We will examine two well-known decision problems (path planning and online learning), and in both cases establish sharp, information-theoretic complexity vs. privacy tradeoff. As a by-product, our analysis also leads to simple yet provably efficient algorithms for both the decision maker and eavesdropping adversary.
Based on joint work with Kuang Xu (Stanford) and Zhi Xu (MIT).
Ioannis Tsitsiklis
Massachusetts Institute of Technology
Safeguarding Privacy in Dynamic Decision-Making Problems
FRIDAY 15/3/2019
11:00 – 12:00
ROOM Τ102, 1st FLOOR,
NEW AUEB BUILDING (TRIAS 2)
ABSTRACT
The increasing ubiquity of large-scale infrastructures for surveillance and data analysis has made understanding the impact of privacy a pressing priority in many domains. We propose a framework for studying a fundamental cost vs. privacy tradeoff in dynamic decision-making problems. The central question is: how can a decision maker take actions that are efficient for her goal, while simultaneously ensuring these actions do not inadvertently reveal her private information, even when observed and analyzed by a powerful adversary? We will examine two well-known decision problems (path planning and online learning), and in both cases establish sharp, information-theoretic complexity vs. privacy tradeoff. As a by-product, our analysis also leads to simple yet provably efficient algorithms for both the decision maker and eavesdropping adversary.
Based on joint work with Kuang Xu (Stanford) and Zhi Xu (MIT).
- 2nd Research Seminar of the AUEB School of Information Sciences & Technology 12/12/2019:
- First One-Day Conference of the School of Information Science of AUEB: Wednesday 17/4/2019
- AUEB INFORMATICS SEMINAR: Causality and Directed Information in Communication, Gambling, Estimation, Inference and Statistical Physics by Haim Permuter
- AUEB CAREΕR MOTIVATION SEMINAR FOR STUDENTS - 12/12/2016: (A) Causal inference in statistics and econometrics & (B) Research Opportunities for Statistics Graduates in the University of Chicago
- AUEB SEMINARS - 30/3/2016: Information fusion approach using signal quality indices, and information-theoretic feature selection: practical approaches and applications
Permissions in this forum:
You cannot reply to topics in this forum