NIPS 2018

Timezone: »

Poster

Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization

Bargav Jayaraman · Lingxiao Wang · David Evans · Quanquan Gu

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #155

in Tue Poster Session B »

Distributed learning allows a group of independent data owners to collaboratively learn a model over their data sets without exposing their private data. We present a distributed learning approach that combines differential privacy with secure multi-party computation. We explore two popular methods of differential privacy, output perturbation and gradient perturbation, and advance the state-of-the-art for both methods in the distributed learning setting. In our output perturbation method, the parties combine local models within a secure computation and then add the required differential privacy noise before revealing the model. In our gradient perturbation method, the data owners collaboratively train a global model via an iterative learning algorithm. At each iteration, the parties aggregate their local gradients within a secure computation, adding sufficient noise to ensure privacy before the gradient updates are revealed. For both methods, we show that the noise can be reduced in the multi-party setting by adding the noise inside the secure computation after aggregation, asymptotically improving upon the best previous results. Experiments on real world data sets demonstrate that our methods provide substantial utility gains for typical privacy requirements.

Author Information

Bargav Jayaraman (University of Virginia)

Lingxiao Wang (University of California, Los Angeles)

David Evans (University of Virginia)

Quanquan Gu (UCLA)

More from the Same Authors