Filters








5 Hits in 2.9 sec

Exact Symbolic Inference in Probabilistic Programs via Sum-Product Representations [article]

Feras A. Saad, Martin C. Rinard, Vikash K. Mansinghka
2020 arXiv   pre-print
We present the Sum-Product Probabilistic Language (SPPL), a new system that automatically delivers exact solutions to a broad range of probabilistic inference queries.  ...  SPPL symbolically represents the full distribution on execution traces specified by a probabilistic program using a generalization of sum-product networks.  ...  Sec. 6.2 compares the runtime of conditioning and querying probabilistic programs using Sppl to PSI [Gehr et al. 2016 ], a state-of-the-art tool for exact, fully-symbolic probabilistic inference.  ... 
arXiv:2010.03485v1 fatcat:gezscr56fnduvp4cruul6jiddi

Semi-Symbolic Inference for Efficient Streaming Probabilistic Programming [article]

Eric Atkinson and Charles Yuan and Guillaume Baudart and Louis Mandel and Michael Carbin
2022 arXiv   pre-print
To perform exact and approximate inference together, the semi-symbolic inference system manipulates symbolic distributions to perform exact inference when possible and falls back on approximate sampling  ...  probabilistic programs.  ...  RELATED WORK Exact Inference Systems Some probabilistic programming systems are designed specifically for exact inference.  ... 
arXiv:2209.07490v1 fatcat:s5yrzuzicrgpxaxc77y6eneg5i

Program Analysis of Probabilistic Programs [article]

Maria I. Gorinova
2022 arXiv   pre-print
Probabilistic programming is a growing area that strives to make statistical analysis more accessible, by separating probabilistic modelling from probabilistic inference.  ...  No single inference algorithm can be used as a probabilistic programming back-end that is simultaneously reliable, efficient, black-box, and general.  ...  One major group of such languages is symbolic PPLs, where the inference result is an exact symbolic expression.  ... 
arXiv:2204.06868v1 fatcat:2dbonwruuzaopil4aijdeuz4mi

Program analysis of probabilistic programs [article]

Maria I. Gorinova, University Of Edinburgh, Andrew Gordon, Charles Sutton
2022
Probabilistic programming is a growing area that strives to make statistical analysis more accessible, by separating probabilistic modelling from probabilistic inference.  ...  No single inference algorithm can be used as a probabilistic programming back-end that is simultaneously reliable, efficient, black-box, and general.  ...  One major group of such languages is symbolic PPLs, where the inference result is an exact symbolic expression.  ... 
doi:10.7488/era/2256 fatcat:2ac2wwn4jbdctaebzhgo742ct4

Sequential and parallel algorithms for sequence analysis problems in bioinformatics

Xuan Liu
2022
A huge number of computing algorithms are developed and available now to help with the study of these, and in order to solve these problems more efficiently and accurately, much attention has been paid  ...  , deletion, substitute of a symbol with an other one.  ...  Therefore, lots of researchers have been trying to increase SA's rate of conver gence by fast annealing schedules, that is, with a faster annealing scheme.  ... 
doi:10.26174/thesis.lboro.20027552.v1 fatcat:thu26eslunenvf6s6ri6ydsura