Generalized Accept-Reject sampling schemes
By George Casella, Christian P. Robert, Martin T. Wells. 2004
174 citations recorded by the source corpus.
This paper extends the Accept-Reject algorithm to allow the proposal distribution to change at each iteration. We first establish a necessary and sufficient condition for this generalized Accept-Reject algorithm to be valid, and then show how the resulting estimator can be improved by Rao-Blackwellization. An application of these results is to the perfect sampling technique of Fill (1998), An interruptible algorithm for perfect sampling via Markov chains, which is a generalized Accept-Reject algorithm.
Subfields: Artificial Intelligence, Statistics and Probability, Probabilistic & Bayesian Methods
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Quoc V. Le
- Jascha Narain Sohl-Dickstein
- Mohit Bansal
- Kyunghyun Cho
- Hugo Larochelle
- Sergey Levine
- Aaron C. Courville
In Statistics and Probability
- Jascha Narain Sohl-Dickstein
- Yoshua Bengio
- Hugo Larochelle
- Tong Che
- Alex Graves
- Kyunghyun Cho
- Tijmen Blankevoort
- Rudolph van der Merwe
In Probabilistic & Bayesian Methods
- Yoshua Bengio
- Hugo Larochelle
- Jascha Narain Sohl-Dickstein
- Ruixiang Zhang
- Tong Che
- Aaron C. Courville
- Stefano Ermon
- Yuan Cao
Citations in the corpus
- Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling (2020, methodology): “To derive this formulation, we first review rejection sampling (Casella et al., 2004).”
- Discriminator Rejection Sampling (2018, neutral): “In this case, we can exactly sample from p d (Casella et al., 2004), though we may have to reject many samples to do so.”