重新审视混合模型上草图算子的 RIP 保证
Revisiting RIP guarantees for sketching operators on mixture models
AI总结:
本文针对压缩混合建模中的草图算子,提出仅依赖频率集合的确定性 RIP 界与集中不等式,消除了随机 Fourier 特征采样中的重要性采样假设,并为快速结构化草图提供理论基础。
摘要:
在用于压缩混合建模的草图(sketching)背景下,我们重新审视了草图算子关于某些混合模型的受限等距性质(Restricted Isometry Property,RIP)的现有证明。在考察现有保证的不足之后,我们提出一种替代分析,避免了在抽取随机 Fourier 特征以构建随机草图算子时必须假设重要性采样的需要。我们的分析基于受限等距常数的新的确定性界,这些界仅取决于用于定义草图算子的频率集合;随后,我们利用这些界建立随机草图算子的集中不等式,从而得到所需的 RIP 保证。我们的分析也为与快速随机线性算子相关联的频率所构成的结构化草图的理论保证打开了大门。
英文摘要:
In the context of sketching for compressive mixture modeling, we revisit existing proofs of the Restricted Isometry Property of sketching operators with respect to certain mixtures models. After examining the shortcomings of existing guarantees, we propose an alternative analysis that circumvents the need to assume importance sampling when drawing random Fourier features to build random sketching operators. Our analysis is based on new deterministic bounds on the restricted isometry constant that depend solely on the set of frequencies used to define the sketching operator; then we leverage these bounds to establish concentration inequalities for random sketching operators that lead to the desired RIP guarantees. Our analysis also opens the door to theoretical guarantees for structured sketching with frequencies associated to fast random linear operators.
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。