跳到正文
Apple Machine Learning Research·· 13 天前AI 評分39

理解 Private Evolution 作為學習增強型聚類

Understanding Private Evolution as Learning-Augmented Clustering

AI 導讀

研究將差分私隱演算法 Private Evolution(PE)重新表述為生成模型增強的 Wasserstein 學習,並提出具幾何感知能力的新版本。理論分析顯示,若生成器能在與目標分佈相同的低維空間生成樣本,樣本複雜度便取決於內在維度,而非環境維度;標準 PE 變體則可能無法在簡單的良好聚類案例中收斂。實驗顯示,新算法可與標準基線競爭,並提升召回率。

正文

AuthorsAudra McMillan, Kunal Talwar, Felix Zhou†**

Private Evolution (PE) is a differentially private algorithm for synthetic data generation. While it can be viewed as a Wasserstein learning algorithm, it performs much better in practice than worst-case Wasserstein analyses would predict. We recast PE as generative model-augmented Wasserstein learning. We show theoretically that when we take into account the use of a generative model that is able to capture something about the true distribution, then we can obtain much better performance bounds. For example, if the generator gives samples in the same low-dimensional space as the distribution, then sample complexity depends on intrinsic, not ambient, dimension. We also show that standard variants of PE can fail to converge on simple well-clustered instances, and propose a new geometry-aware version of PE with provable convergence on such instances. Experimentally, we show that our new algorithm is competitive with standard baselines and can improve recall.

  • † Yale University
  • ** Work done while at Apple

Related readings and updates.

Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein distance is an appropriate error metric for density estimation. For example, when estimating population densities in a geographic region, a small Wasserstein distance means that the estimate is able to capture roughly where the population mass is. In this work we study differentially private density estimation…

Read more

Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein distance is an appropriate error metric for density estimation. For example, when estimating population densities in a geographic region, a small Wasserstein distance means that the estimate is able to capture roughly where the population mass is. In this work we study differentially private density estimation…

Read more

來源:Apple Machine Learning Research · machinelearning.apple.com