arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.09699cs.LGcs.CRmath.OCstat.ML
收藏

私人(随机)非凸优化:二阶平稳点和超额风险

Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks

Google Research(谷歌研究院);University of Washington(华盛顿大学)

Arun Ganesh, Daogao Liu, Sewoong Oh, Abhradeep Thakurta

摘要:

我们考虑的问题,最小化的非凸目标,同时保持隐私的例子中的训练数据。在以前的方差减少算法SpiderBoost的基础上,我们引入了一个新的框架,利用两种不同的梯度预言。第一种预言机可以估计一个点的梯度,第二种预言机,精度较低,成本较低,可以估计两点之间的梯度差。SpiderBoost定期使用第一种,每隔几步使用一次,而我们的框架建议在总漂移变大时使用第一个预言,否则依赖于第二个预言。这种新的框架确保梯度估计始终保持准确,从而提高了找到二阶稳定点的速度。此外,我们解决了一个更具挑战性的任务,找到一个非凸目标的全局最小值使用指数机制。我们的研究结果表明,正则化的指数机制可以密切匹配以前的经验和人口的风险界限,而不需要平滑假设的算法与多项式运行时间。此外,通过忽略运行时间的考虑,我们表明,指数机制可以实现一个很好的人口风险界,并提供一个几乎匹配的下限。

英文摘要:

We consider the problem of minimizing a non-convex objective while preserving the privacy of the examples in the training data. Building upon the previous variance-reduced algorithm SpiderBoost, we introduce a new framework that utilizes two different kinds of gradient oracles. The first kind of oracles can estimate the gradient of one point, and the second kind of oracles, less precise and more cost-effective, can estimate the gradient difference between two points. SpiderBoost uses the first kind periodically, once every few steps, while our framework proposes using the first oracle whenever the total drift has become large and relies on the second oracle otherwise. This new framework ensures the gradient estimations remain accurate all the time, resulting in improved rates for finding second-order stationary points. Moreover, we address a more challenging task of finding the global minima of a non-convex objective using the exponential mechanism. Our findings indicate that the regularized exponential mechanism can closely match previous empirical and population risk bounds, without requiring smoothness assumptions for algorithms with polynomial running time. Furthermore, by disregarding running time considerations, we show that the exponential mechanism can achieve a good population risk bound and provide a nearly matching lower bound.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑