Differentially-Private Bayes Consistency
Abstract
We construct a universally Bayes consistent learning rule
which satisfies differential privacy (DP).
We first handle the setting of binary classification
and then extend our rule to the more
general setting of density estimation (with respect to the total variation metric).
The existence of a universally consistent DP learner
reveals a stark difference with the distribution-free PAC model.
Indeed, in the latter DP learning is extremely limited:
even one-dimensional linear classifiers
are not privately learnable in this stringent model.
Our result thus demonstrates that by allowing
the learning rate to depend on the target distribution,
one can circumvent the above-mentioned impossibility result
and in fact learn \emph{arbitrary} distributions by a single DP algorithm.
As an application, we prove that any VC class can be privately learned in a semi-supervised
setting with a near-optimal \emph{labelled} sample complexity of $\tilde O(d/\eps)$ labeled examples
(and with an unlabeled sample complexity that can depend on the target distribution).
which satisfies differential privacy (DP).
We first handle the setting of binary classification
and then extend our rule to the more
general setting of density estimation (with respect to the total variation metric).
The existence of a universally consistent DP learner
reveals a stark difference with the distribution-free PAC model.
Indeed, in the latter DP learning is extremely limited:
even one-dimensional linear classifiers
are not privately learnable in this stringent model.
Our result thus demonstrates that by allowing
the learning rate to depend on the target distribution,
one can circumvent the above-mentioned impossibility result
and in fact learn \emph{arbitrary} distributions by a single DP algorithm.
As an application, we prove that any VC class can be privately learned in a semi-supervised
setting with a near-optimal \emph{labelled} sample complexity of $\tilde O(d/\eps)$ labeled examples
(and with an unlabeled sample complexity that can depend on the target distribution).
Research Areas
