Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties

Details Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties

2010-06-21

arxiv.org/abs/1006.4039v3

Computer Science

Learning

25 pages, 2 figures

Scientific paper

Online learning has become increasingly popular on handling massive data. The sequential nature of online learning, however, requires a centralized learner to store data and update parameters. In this paper, we consider online learning with {\em distributed} data sources. The autonomous learners update local parameters based on local data sources and periodically exchange information with a small subset of neighbors in a communication network. We derive the regret bound for strongly convex functions that generalizes the work by Ram et al. (2010) for convex functions. Most importantly, we show that our algorithm has \emph{intrinsic} privacy-preserving properties, and we prove the sufficient and necessary conditions for privacy preservation in the network. These conditions imply that for networks with greater-than-one connectivity, a malicious learner cannot reconstruct the subgradients (and sensitive raw data) of other learners, which makes our algorithm appealing in privacy sensitive applications.

Affiliated with

Also associated with

No associations

Rating

Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties 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 Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-601195