Public-data Assisted Private Stochastic Optimization: Power and Limitations
This work addresses the challenge of leveraging public data to improve private machine learning, with incremental contributions to understanding limits and developing efficient algorithms for specific models.
The paper tackles the problem of stochastic convex optimization with public data under differential privacy, establishing lower bounds that show simple strategies are optimal for labeled public data, and presents novel methods for unlabeled public data in supervised learning, achieving dimension-independent rates with specific sample complexities.
We study the limits and capability of public-data assisted differentially private (PA-DP) algorithms. Specifically, we focus on the problem of stochastic convex optimization (SCO) with either labeled or unlabeled public data. For complete/labeled public data, we show that any $(ε,δ)$-PA-DP has excess risk $\tildeΩ\big(\min\big\{\frac{1}{\sqrt{n_{\text{pub}}}},\frac{1}{\sqrt{n}}+\frac{\sqrt{d}}{nε} \big\} \big)$, where $d$ is the dimension, ${n_{\text{pub}}}$ is the number of public samples, ${n_{\text{priv}}}$ is the number of private samples, and $n={n_{\text{pub}}}+{n_{\text{priv}}}$. These lower bounds are established via our new lower bounds for PA-DP mean estimation, which are of a similar form. Up to constant factors, these lower bounds show that the simple strategy of either treating all data as private or discarding the private data, is optimal. We also study PA-DP supervised learning with \textit{unlabeled} public samples. In contrast to our previous result, we here show novel methods for leveraging public data in private supervised learning. For generalized linear models (GLM) with unlabeled public data, we show an efficient algorithm which, given $\tilde{O}({n_{\text{priv}}}ε)$ unlabeled public samples, achieves the dimension independent rate $\tilde{O}\big(\frac{1}{\sqrt{n_{\text{priv}}}} + \frac{1}{\sqrt{n_{\text{priv}}ε}}\big)$. We develop new lower bounds for this setting which shows that this rate cannot be improved with more public samples, and any fewer public samples leads to a worse rate. Finally, we provide extensions of this result to general hypothesis classes with finite fat-shattering dimension with applications to neural networks and non-Euclidean geometries.