New way to learn data patterns while protecting individual privacy
Researchers developed efficient algorithms to estimate discrete distributions under person-level differential privacy.
Researchers studied how to learn a discrete distribution under person-level differential privacy in a batched setting. They want to estimate a distribution over $[k]$ with a total-variation error .
The study involves users. Each user provides i.i.d. samples from the unknown distribution .
The algorithms use a new degree-6 sum-of-squares estimator. This estimator learns from untrusted batches. It uses a trace-bounded diagonal majorizer for the difference between empirical covariance and multinomial covariance.
The researchers used semidefinite-programming duality and a symmetric form of Grothendieck's inequality. These tools prove that clean data admit a specific certificate. This certificate preserves the mean-dependent variance of multinomial batch averages.
Under pure -DP, the algorithm achieves . This matches the information-theoretic optimum up to logarithmic factors.
Under approximate -DP, the algorithm achieves . A statistical query lower bound rules out a uniformly smaller order of error under fixed polynomial SQ resource bounds.
Key facts
- The algorithms work under both pure and approximate differential privacy.
- The pure differential privacy guarantee matches the information-theoretic optimum up to logarithmic factors.
- A statistical query lower bound rules out a uniformly smaller order of error under fixed polynomial SQ resource bounds.