Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity
This work addresses sample efficiency in private statistical inference, providing a significant improvement for researchers and practitioners in privacy-preserving machine learning.
The paper tackles the problem of hypothesis selection under local differential privacy, achieving an optimal sample complexity of Θ(k/(α²min{ε²,1})) for ε<1, which improves over previous algorithms by a factor of log k and demonstrates the benefits of interaction with only Θ(log log k) rounds.
We study the problem of hypothesis selection under the constraint of local differential privacy. Given a class $\mathcal{F}$ of $k$ distributions and a set of i.i.d. samples from an unknown distribution $h$, the goal of hypothesis selection is to pick a distribution $\hat{f}$ whose total variation distance to $h$ is comparable with the best distribution in $\mathcal{F}$ (with high probability). We devise an $\varepsilon$-locally-differentially-private ($\varepsilon$-LDP) algorithm that uses $Θ\left(\frac{k}{α^2\min \{\varepsilon^2,1\}}\right)$ samples to guarantee that $d_{TV}(h,\hat{f})\leq α+ 9 \min_{f\in \mathcal{F}}d_{TV}(h,f)$ with high probability. This sample complexity is optimal for $\varepsilon<1$, matching the lower bound of Gopi et al. (2020). All previously known algorithms for this problem required $Ω\left(\frac{k\log k}{α^2\min \{ \varepsilon^2 ,1\}} \right)$ samples to work. Moreover, our result demonstrates the power of interaction for $\varepsilon$-LDP hypothesis selection. Namely, it breaks the known lower bound of $Ω\left(\frac{k\log k}{α^2\min \{ \varepsilon^2 ,1\}} \right)$ for the sample complexity of non-interactive hypothesis selection. Our algorithm breaks this barrier using only $Θ(\log \log k)$ rounds of interaction. To prove our results, we define the notion of \emph{critical queries} for a Statistical Query Algorithm (SQA) which may be of independent interest. Informally, an SQA is said to use a small number of critical queries if its success relies on the accuracy of only a small number of queries it asks. We then design an LDP algorithm that uses a smaller number of critical queries.