Instance Dependent Testing of Samplers using Interval Conditioning
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers
We consider the sampling problem, where the aim is to draw samples from a distribution whose density is known only up to a normalization constant. Recent breakthroughs in generative modeling to approximate a high-dimensi…
A Flexible Framework for Hypothesis Testing in High-dimensions
Hypothesis testing in the linear regression model is a fundamental statistical problem. We consider linear regression in the high-dimensional regime where the number of parameters exceeds the number of samples ($p> n$). …
regressionTwo-sample testingvalidVocal Bursts Intensity PredictionCorrected Samplers for Discrete Flow Models
Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alternative to discrete diffusion models. A line of recent work has studied sampler…
Text-to-Image GenerationProbabilistic Programs with Stochastic Conditioning
We tackle the problem of conditioning probabilistic programs on distributions of observable variables. Probabilistic programs are usually conditioned on samples from the joint data distribution, which we refer to as dete…
Probabilistic ProgrammingSampling with Mirrored Stein Operators
We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries. Stein Variational Mirror Descent and Mirrored Stein Variational Gradient Descent minimize the Kullba…
valid