226,733 Hits in 4.5 sec

Using probabilistic programs as proposals [article]

Marco F. Cusumano-Towner, Vikash K. Mansinghka
2018 arXiv   pre-print
Support for optimizing and using proposal programs is easily implemented in a sampling-based probabilistic programming runtime.  ...  Proposal programs can be used as proposal distributions in importance sampling and Metropolis-Hastings samplers without sacrificing asymptotic consistency, and can be optimized offline using inference  ...  We propose to use probabilistic programming languages as a medium for users to encode their domain-specific knowledge about the posterior, and to learn parameters of the program offline using an amortized  ... 
arXiv:1801.03612v2 fatcat:i6tjdve2brdpjjgxcy2365leky

Flexible Probabilistic Modeling for Search Based Test Data Generation

Robert Feldt, Shin Yoo
2020 Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops  
In particular, Probabilistic Programming languages (PPLs) and Genetic Programming (GP) should be investigated since they allow for very flexible probabilistic modelling.  ...  While Search-Based Software Testing (SBST) has improved significantly in the last decade we propose that more flexible, probabilistic models can be leveraged to improve it further.  ...  We propose a novel use of Probabilistic Programming Language as a means to express generative models.  ... 
doi:10.1145/3387940.3392215 dblp:conf/icse/FeldtY20 fatcat:4xdujt2gy5budmkqh4bykkcejm

Applications of Probabilistic Programming (Master's thesis, 2015) [article]

Yura N Perov
2020 arXiv   pre-print
In Chapter 3, we describe a way to facilitate sequential Monte Carlo inference in probabilistic programming using data-driven proposals.  ...  We also explore the possibility of using neural networks to improve data-driven proposals.  ...  Data-driven proposals in probabilistic programming As discussed in Chapter 1, to make probabilistic programming more efficient and widely used by the machine learning community, we need to enhance the  ... 
arXiv:1606.00075v2 fatcat:bwargqfv25fjplh53spm7aitbe

Gen: a general-purpose probabilistic programming system with programmable inference

Marco F. Cusumano-Towner, Feras A. Saad, Alexander K. Lew, Vikash K. Mansinghka
2019 Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation - PLDI 2019  
distributions also written as programs in Gen.  ...  This Work We introduce Gen, a probabilistic programming system that uses a novel approach in which (i) users define probabilistic models in one or more embedded probabilistic DSLs and (ii) users implement  ...  Custom proposal distributions are defined as generative functions using the same probabilistic DSLs used to define probabilistic models.  ... 
doi:10.1145/3314221.3314642 dblp:conf/pldi/Cusumano-Towner19 fatcat:bmjwmh7jhjf33gg6dywrdjop7y

Verifying Weak Probabilistic Noninterference

Ali A., Jaber Karimpour, Ayaz Isazadeh, Shahriar Lotfi
2017 International Journal of Advanced Computer Science and Applications  
Behavior of multi-threaded programs is modeled using probabilistic Kripke structures and formalize weak probabilistic noninterference in terms of these structures.  ...  Smith [9] proposes a new type system to enforce probabilistic noninterference for multi-threaded programs running under a uniform probabilistic scheduler.  ...  As future work, we plan to use the proposed algorithm to verify other information flow properties.  ... 
doi:10.14569/ijacsa.2017.081026 fatcat:mef4uuk6frbvji4d2fegyinfmy

Inference Compilation and Universal Probabilistic Programming [article]

Tuan Anh Le, Atilim Gunes Baydin, Frank Wood
2017 arXiv   pre-print
Our training objective and learning procedure are designed to allow the trained neural network to be used as a proposal distribution in a sequential importance sampling inference engine.  ...  We introduce a method for using deep neural networks to amortize the cost of inference in models from the family induced by universal probabilistic programming languages, establishing a framework that  ...  Acknowledgements We would like to thank Hakan Bilen for his help with the MatConvNet setup and showing us how to use his Fast R-CNN implementation and Tom Rainforth for his helpful advice.  ... 
arXiv:1610.09900v2 fatcat:e6cyizuc2fcypltpcr3x6pucoa

Probabilistic distribution models for EDA-based GP

Kohsuke Yanai, Hitoshi Iba
2005 Proceedings of the 2005 conference on Genetic and evolutionary computation - GECCO '05  
This paper proposes a novel technique for a program evolution based on probabilistic models.  ...  In the proposed method, two probabilistic distribution models with probabilistic dependencies between variables are used together.  ...  INTRODUCTION In this paper, we propose Extended Estimation of Distribution Programming (XEDP), which can be viewed as an extension of EDP [4] .  ... 
doi:10.1145/1068009.1068305 dblp:conf/gecco/YanaiI05 fatcat:tsenwquxb5d2nkmt2jwplz5rui

Universal Marginaliser for Deep Amortised Inference for Probabilistic Programs [article]

Robert Walecki, Kostis Gourgoulias, Adam Baker, Chris Hart, Chris Lucas, Max Zwiessele, Albert Buchard, Maria Lomeli, Yura Perov, Saurabh Johri
2019 arXiv   pre-print
We show how combining samples drawn from the original probabilistic program prior with an appropriate augmentation method allows us to train one neural network to approximate any of the corresponding conditional  ...  Finally, we benchmark the method on multiple probabilistic programs, in Pyro, with different model structure.  ...  This abstract proposes an idea of automatic generation and training of a neural network given a probabilistic program and samples from its prior, such that one neural network can be used as a proposal  ... 
arXiv:1910.07474v1 fatcat:s5okn32phvg3diyoisfwnuokbi

Reversible Jump Probabilistic Programming

David A. Roberts, Marcus Gallagher, Thomas Taimre
2019 International Conference on Artificial Intelligence and Statistics  
In this paper we present a method for automatically deriving a Reversible Jump Markov chain Monte Carlo sampler from probabilistic programs that specify the target and proposal distributions.  ...  We also present Stochaskell, a new probabilistic programming language embedded in Haskell, which provides an implementation of our method.  ...  This research was supported by an Australian Government Research Training Program Scholarship.  ... 
dblp:conf/aistats/RobertsGT19 fatcat:e2nh7ke7pvfbfcu23qa2m7eevi

SYMPAIS: SYMbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis [article]

Yicheng Luo, Antonio Filieri, Yuan Zhou
2020 arXiv   pre-print
Probabilistic software analysis aims at quantifying the probability of a target event occurring during the execution of a program processing uncertain incoming data or written itself using probabilistic  ...  programming constructs.  ...  Probabilistic software analysis extends classic static analyses techniques to consider the e ects of probabilistic uncertainty, whether explicitly embedded within the code -as in probabilistic program  ... 
arXiv:2010.05050v1 fatcat:ib3bc7ygrzhsvh3m54i6ekexhi

Picture: A probabilistic programming language for scene perception

Tejas D Kulkarni, Pushmeet Kohli, Joshua B Tenenbaum, Vikash Mansinghka
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Here we present Picture, a probabilistic programming language for scene understanding that allows researchers to express complex generative vision models, while automatically solving them using fast general-purpose  ...  We use Picture to write programs for 3D face analysis, 3D human pose estimation, and 3D object reconstruction -each competitive with specially engineered baselines.  ...  Acknowledgements We thank Thomas Vetter for giving us access to the Basel face model. T. Kulkarni was graciously supported by the Leventhal Fellowship.  ... 
doi:10.1109/cvpr.2015.7299068 dblp:conf/cvpr/KulkarniKTM15 fatcat:kwyidcyug5esxiu5jykt6knim4

Instruction sequence notations with probabilistic instructions [article]

J. A. Bergstra, C. A. Middelburg
2014 arXiv   pre-print
We propose several kinds of probabilistic instructions, provide an informal operational meaning for each of them, and discuss related work.  ...  On purpose, we refrain from providing an ad hoc formal meaning for the proposed kinds of instructions.  ...  The refinement oriented theory of programs uses demonic choice, usually written ⊓, as a primitive (see e.g. [30, 31] ).  ... 
arXiv:0906.3083v2 fatcat:bsfhmph2bvhz3b4axci2dsn75q

Inference Over Programs That Make Predictions [article]

Yura Perov
2018 arXiv   pre-print
This abstract extends on the previous work (arXiv:1407.2646, arXiv:1606.00075) on program induction using probabilistic programming.  ...  It describes possible further steps to extend that work, such that, ultimately, automatic probabilistic program synthesis can generalise over any reasonable set of inputs and outputs, in particular in  ...  Acknowledgments This abstract is the extension to the work [21] , as well as incorporates ideas which had been published online [18] [19] [20] .  ... 
arXiv:1810.01190v1 fatcat:mur6mjffbza4xp2dbu6aattzbu

Solving Multi-Objective Probabilistic Factional Programming Problem

2019 International Journal of Engineering and Advanced Technology  
using analytical methods.  ...  In the proposed method, it is not necessary to find the deterministic equivalent of a probabilistic programming problem and applying any traditional methods of fractional programming problem.  ...  To avoid this drawback, Iwamura and Liu [8] proposed a genetic algorithm for probabilistic programming problem including probabilistic goal programming, probabilistic multi objective programming problem  ... 
doi:10.35940/ijeat.f1162.0986s319 fatcat:4xxroc3cczhrffgo24bau6wtlq

Nonstandard Interpretations of Probabilistic Programs for Efficient Inference

David Wingate, Noah D. Goodman, Andreas Stuhlmüller, Jeffrey Mark Siskind
2011 Neural Information Processing Systems  
Probabilistic programming languages allow modelers to specify a stochastic process using syntax that resembles modern programming languages.  ...  We show how nonstandard interpretations of probabilistic programs can be used to craft efficient inference algorithms: information about the structure of a distribution (such as gradients or dependencies  ...  Introduction Probabilistic programming simplifies the development of probabilistic models by allowing modelers to specify a stochastic process using syntax that resembles modern programming languages.  ... 
dblp:conf/nips/WingateGSS11 fatcat:lcprhupt5rfn3axo6fpj4glnfy
« Previous Showing results 1 — 15 out of 226,733 results