Distributed Learning, Communication Complexity and Privacy
Maria-Florina Balcan, Avrim L. Blum, Shai Fine et al. · arXiv (Cornell University) · 2012
We consider the problem of PAC-learning from distributed data and analyze fundamental communication complexity questions involved. We provide general upper and lower bounds on the amount of communication needed to learn well, showing that in addition to VC-dimension and covering number, quantities such as the teaching-dimension and mistake-bound of a class play an important role. We also present tight results for a number of common concept classes including conjunctions, parity functions, and decision lists. For linear separators, we show that for non-concentrated distributions, we can use a version of the Perceptron algorithm to learn with much less communication than the number of updates given by the usual margin bound. We also show how boosting can be performed in a generic manner in the distributed setting to achieve communication with only logarithmic dependence on 1/epsilon for any concept class, and demonstrate how recent work on agnostic learning from class-conditional queries can be used to achieve low communication in agnostic settings as well. We additionally present an analysis of privacy, considering both differential privacy and a notion of distributional privacy that is especially appealing in this context.
Cited by 104 works. doi:10.1184/r1/6475568 Open-access PDF
Authors
References
- A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
- The Strength of Weak Learnability
- Differential Privacy
- Logistic Regression, AdaBoost and Bregman Distances
- Differential Privacy: A Survey of Results
- Practical privacy
- Parallelized Stochastic Gradient Descent
- Privacy-Preserving Datamining on Vertically Partitioned Databases
- Efficient noise-tolerant learning from statistical queries
- A learning theory approach to non-interactive database privacy