Computer Science – Learning
Scientific paper
2008-03-06
Computer Science
Learning
35 pages, 2 figures
Scientific paper
Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept classes can be learned privately, namely, by an algorithm whose output does not depend too heavily on any one input or specific training example? More precisely, we investigate learning algorithms that satisfy differential privacy, a notion that provides strong confidentiality guarantees in contexts where aggregate information is released about a database containing sensitive information about individuals. We demonstrate that, ignoring computational constraints, it is possible to privately agnostically learn any concept class using a sample size approximately logarithmic in the cardinality of the concept class. Therefore, almost anything learnable is learnable privately: specifically, if a concept class is learnable by a (non-private) algorithm with polynomial sample complexity and output size, then it can be learned privately using a polynomial number of samples. We also present a computationally efficient private PAC learner for the class of parity functions. Local (or randomized response) algorithms are a practical class of private algorithms that have received extensive investigation. We provide a precise characterization of local private learning algorithms. We show that a concept class is learnable by a local algorithm if and only if it is learnable in the statistical query (SQ) model. Finally, we present a separation between the power of interactive and noninteractive local learning algorithms.
Kasiviswanathan Shiva Prasad
Lee Homin K.
Nissim Kobbi
Raskhodnikova Sofya
Smith Adam
No associations
LandOfFree
What Can We Learn Privately? does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with What Can We Learn Privately?, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and What Can We Learn Privately? will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-14348