Generalization in the Face of Adaptivity: A Bayesian Perspective

Understand

Repeated use of a data sample via adaptively chosen queries can rapidly lead to overfitting, wherein the empirical evaluation of queries on the sample significantly deviates from their mean with respect to the underlying data distribution.

• It turns out that simple noise addition algorithms suffice to prevent this issue, and differential privacy-based analysis of these algorithms shows that they can handle an asymptotically optimal number of queries.
• However, differential privacy's worst-case nature entails scaling such noise to the range of the queries even for highly-concentrated queries, or introducing more complex algorithms.
• In this paper, we prove that straightforward noise-addition algorithms already provide variance-dependent guarantees that also extend to unbounded queries.