Locally Optimal Private Sampling: Beyond the Global Minimax
This work addresses the challenge of generating realistic data under strong privacy constraints for applications like private sampling with public data, representing an incremental advance by refining prior global approaches to a local perspective.
The paper tackles the problem of sampling from a distribution under local differential privacy by focusing on local minimax optimality around a fixed distribution, rather than global optimality across all distributions. It shows that the local minimax risk equals the global minimax risk when restricted to a neighborhood, derives a closed-form expression for optimal samplers, and empirically demonstrates that these local samplers consistently outperform global methods.
We study the problem of sampling from a distribution under local differential privacy (LDP). Given a private distribution $P \in \mathcal{P}$, the goal is to generate a single sample from a distribution that remains close to $P$ in $f$-divergence while satisfying the constraints of LDP. This task captures the fundamental challenge of producing realistic-looking data under strong privacy guarantees. While prior work by Park et al. (NeurIPS'24) focuses on global minimax-optimality across a class of distributions, we take a local perspective. Specifically, we examine the minimax risk in a neighborhood around a fixed distribution $P_0$, and characterize its exact value, which depends on both $P_0$ and the privacy level. Our main result shows that the local minimax risk is determined by the global minimax risk when the distribution class $\mathcal{P}$ is restricted to a neighborhood around $P_0$. To establish this, we (1) extend previous work from pure LDP to the more general functional LDP framework, and (2) prove that the globally optimal functional LDP sampler yields the optimal local sampler when constrained to distributions near $P_0$. Building on this, we also derive a simple closed-form expression for the locally minimax-optimal samplers which does not depend on the choice of $f$-divergence. We further argue that this local framework naturally models private sampling with public data, where the public data distribution is represented by $P_0$. In this setting, we empirically compare our locally optimal sampler to existing global methods, and demonstrate that it consistently outperforms global minimax samplers.