实例依赖测试的采样器使用区间条件
Instance Dependent Testing of Samplers using Interval Conditioning
AI总结:
本文提出了一种新的实例依赖测试方法,用于验证采样器在自然数域上的效率,通过区间条件框架实现,实验显示速度提升达1000倍。
摘要:
采样算法在概率AI中起着关键作用。然而,验证一个采样程序是否确实从声称的分布中采样是一个 notoriously 难的问题。只有在最近几年才提出了诸如Barbarik、Teq、Flash、CubeProbe等可证明正确的测试器,用于测试不同类型的采样器。所有这些测试器都关注最坏情况下的效率,不支持在无限域上验证采样器,这在天文学、金融、网络安全等领域经常出现。在本工作中,我们设计了第一个具有实例依赖效率的测试器,允许我们对自然数进行测试。我们的测试是通过一种新颖的距离估计算法来估计未知和已知概率分布之间的距离,使用区间条件框架。核心技术贡献是与连续分布的概率质量估计的新联系。实际收益也相当可观:我们的实验表明,与最先进的测试器相比,速度提升了高达1000倍。
英文摘要:
Sampling algorithms play a pivotal role in probabilistic AI. However, verifying if a sampler program indeed samples from the claimed distribution is a notoriously hard problem. Provably correct testers like Barbarik, Teq, Flash, CubeProbe for testing of different kinds of samplers were proposed only in the last few years. All these testers focus on the worst-case efficiency, and do not support verification of samplers over infinite domains, a case occurring frequently in Astronomy, Finance, Network Security, etc. In this work, we design the first tester of samplers with instance-dependent efficiency, allowing us to test samplers over natural numbers. Our tests are developed via a novel distance estimation algorithm between an unknown and a known probability distribution using an interval conditioning framework. The core technical contribution is a new connection with probability mass estimation of a continuous distribution. The practical gains are also substantial: our experiments establish up to 1000x speedup over state-of-the-art testers.
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。