The development of efficient sampling algorithms catering to non-Euclidean geometries has been a challenging endeavor, as discretization techniques which succeed in the Euclidean setting do not readily carry over to more general settings. We develop a non-Euclidean analog of the recent proximal sampler of [LST21], which naturally induces regularization by an object known as the log-Laplace transform (LLT) of a density. We prove new mathematical properties (with an algorithmic flavor) of the LLT, such as strong convexity-smoothness duality and an isoperimetric inequality, which are used to prove a mixing time on our proximal sampler matching [LST21] under a warm start. As our main application, we show our warm-started sampler improves the value oracle complexity of differentially private convex optimization in $\ell_p$ and Schatten-$p$ norms for $p \in [1, 2]$ to match the Euclidean setting [GLL22], while retaining state-of-the-art excess risk bounds [GLLST23]. We find our investigation of the LLT to be a promising proof-of-concept of its utility as a tool for designing samplers, and outline directions for future exploration.
翻译:开发适合非欧洲地貌的高效采样算法是一项具有挑战性的努力,因为在欧几里德环境下成功的离散技术不会轻易地传到更一般的设置中。 我们开发了最近[LST21] 的近似准采样器的非欧几里德类仿真,这自然会通过一个称为“日志-拉普特变换”(LLLT)密度的物体进行正规化。 我们证明LLT具有新的数学特性(有算法味),例如强的同化光度双轨和偏差不平等,用来在温暖的开端下证明我们最准采样器匹配[LST21]的混合时间。作为我们的主要应用,我们展示了我们的热点采样器,用$/美元和Schat-10美元标准,以匹配Euclidean 设置[GLL22] 和偏差的不平等,用来证明我们最接近的采样器的混合时间。我们为23号样本设计了一个有前途的试样图案方向,我们找到了一个有希望的探索工具。