Generating Efficient MCMC Kernels from Probabilistic Programs
By Lingfeng Yang, P. Hanrahan, Noah D. Goodman. 2014
31 citations recorded by the source corpus.
Subfields: 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 Probabilistic & Bayesian Methods
- Yura N. Perov
- Frank D. Wood
- Hongseok Yang
- Jan-Willem van de Meent
- Brooks Paige
- David Tolpin
- Vikash K. Mansinghka
- Alexander K. Lew
Citations in the corpus
- An Introduction to Probabilistic Programming (2018, background): “Implementing HMC in a higher-order programming language safely requires explicitly separating the latent random variables into those which are “structure preserving” (Yang et al., 2014), i.”
- Design and Implementation of Probabilistic Programming Language Anglican (2016, methodology): “Among the available inference algorithms there are Particle Cascade (Paige et al. 2014), Lightweight Metropolis-Hastings (Wingate et al. 2011), Iterative Conditional Sequential Monte-Carlo (Particle Gibbs) (Wood et al. 2014), and others.”
- Probabilistic Programming in Anglican (2015, methodology): “Among the available inference algorithms there are Particle Cascade [6], Lightweight Metropolis-Hastings [8], Iterative Conditional Sequential Monte-Carlo (Particle Gibbs) [9], and others.”
- Applications of Probabilistic Programming (Master's thesis, 2015) (2016, methodology): “Furthermore, ways have been proposed to enhance the design of existing inference algorithms, e.g. by exploring conditional dependencies and making incremental updates only on a part of the execution trace, as in Venture (Perov and Mansinghka, 2012; Mansinghka et al., 2014) and Shred (Yang et al., 20”
- Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs (2015, methodology): “To discuss when this is the case, we invoke the concept of structural versus structure-preserving random choices [17].”
- Gen: a general-purpose probabilistic programming system with programmable inference (2019, methodology): “However, existing systems either lack Gen’s modeling flexibility [29], are restricted to single-variable updates [51, 69], and/or have very high runtime overhead [40].”