Abstract | ||
---|---|---|
Several recent studies in privacy-preserving learning have considered the
trade-off between utility or risk and the level of differential privacy
guaranteed by mechanisms for statistical query processing. In this paper we
study this trade-off in private Support Vector Machine (SVM) learning. We
present two efficient mechanisms, one for the case of finite-dimensional
feature mappings and one for potentially infinite-dimensional feature mappings
with translation-invariant kernels. For the case of translation-invariant
kernels, the proposed mechanism minimizes regularized empirical risk in a
random Reproducing Kernel Hilbert Space whose kernel uniformly approximates the
desired kernel with high probability. This technique, borrowed from large-scale
learning, allows the mechanism to respond with a finite encoding of the
classifier, even when the function class is of infinite VC dimension.
Differential privacy is established using a proof technique from algorithmic
stability. Utility--the mechanism's response function is pointwise
epsilon-close to non-private SVM with probability 1-delta--is proven by
appealing to the smoothness of regularized empirical risk minimization with
respect to small perturbations to the feature mapping. We conclude with a lower
bound on the optimal differential privacy of the SVM. This negative result
states that for any delta, no mechanism can be simultaneously
(epsilon,delta)-useful and beta-differentially private for small epsilon and
small beta. |
Year | Venue | Keywords |
---|---|---|
2009 | Clinical Orthopaedics and Related Research | support vector machines |
DocType | Volume | Citations |
Journal | abs/0911.5 | 31 |
PageRank | References | Authors |
1.66 | 20 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Benjamin I. P. Rubinstein | 1 | 486 | 41.87 |
Peter L. Bartlett | 2 | 5482 | 1039.97 |
Ling Huang | 3 | 2496 | 118.80 |
Nina Taft | 4 | 2109 | 154.92 |