Filters








138 Hits in 4.7 sec

Delayed Sampling and Automatic Rao-Blackwellization of Probabilistic Programs [article]

Lawrence M. Murray, Daniel Lundén, Jan Kudlicka, David Broman, Thomas B. Schön
2018 arXiv   pre-print
For inference with Sequential Monte Carlo, this automatically yields improvements such as locally-optimal proposals and Rao-Blackwellization.  ...  We have implemented the approach in Anglican and a new probabilistic programming language called Birch.  ...  Code is included for the pedagogical examples in both Anglican and Birch, and for the empirical case studies, along with data sets, in Birch only.  ... 
arXiv:1708.07787v2 fatcat:jjlapiqjczfkzeobngf55hh5ri

Robust Real-Time Multiple Target Tracking [chapter]

Nicolai von Hoyningen-Huene, Michael Beetz
2010 Lecture Notes in Computer Science  
Using predicted target positions by Kalman filters, data associations are sampled for each measurement sweep according to their likelihood allowing to constrain the number of associations per target.  ...  Fixed-lag of the resulting positions increases the tracking quality while smart resampling and memoization decrease the computational demand.  ...  Khan et al. proposed in [1, 8] a real-time Rao-Blackwellized MCMC-based particle filter allowing also sampling of split and merged measurement associations.  ... 
doi:10.1007/978-3-642-12304-7_24 fatcat:fhiuak4nk5hcxfecapl5xtqjbm

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
In this work, we propose semi-symbolic inference, a technique for executing probabilistic programs using a runtime inference system that automatically implements Rao-Blackwellized particle filtering.  ...  Efficient inference is often possible in a streaming context using Rao-Blackwellized particle filters (RBPFs), which exactly solve inference problems when possible and fall back on sampling approximations  ...  Developers can use this guarantee to reliably write probabilistic programs that the semi-symbolic runtime inference system will automatically implement as Rao-Blackwellized particle filters.  ... 
arXiv:2209.07490v1 fatcat:s5yrzuzicrgpxaxc77y6eneg5i

Probabilistic programming for birth-death models of evolution using an alive particle filter with delayed sampling [article]

Jan Kudlicka and Lawrence M. Murray and Fredrik Ronquist and Thomas B. Schön
2021 arXiv   pre-print
Rao-Blackwellization via delayed sampling.  ...  We consider probabilistic programming for birth-death models of evolution and introduce a new widely-applicable inference method that combines an extension of the alive particle filter (APF) with automatic  ...  This research was financially supported by the Swedish Foundation for Strategic Research (SSF) via the project ASSEMBLE and by the Swedish Research Council grants 2013-4853, 2014-05901 and 2017-03807.  ... 
arXiv:1907.04615v3 fatcat:k2e67hudpna3dcpvcbk5xtrigy

Functional Tensors for Probabilistic Programming [article]

Fritz Obermeyer, Eli Bingham, Martin Jankowiak, Du Phan, Jonathan P. Chen
2020 arXiv   pre-print
It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework.  ...  We demonstrate the versatility of functional tensors by integrating them into the modeling frontend and inference backend of the Pyro programming language.  ...  Lawrence M Murray, Daniel Lundén, Jan Kudlicka, David Broman, and Thomas B Schön. Delayed sampling and automatic rao-blackwellization of probabilistic programs.  ... 
arXiv:1910.10775v2 fatcat:lotryn2vtzcyzg45derogdr4b4

Reactive probabilistic programming

Guillaume Baudart, Louis Mandel, Eric Atkinson, Benjamin Sherman, Marc Pouzet, Michael Carbin
2020 Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation  
We also redesign the delayed sampling inference algorithm to provide efficient streaming inference.  ...  We propose a measure-theoretic semantics of probabilistic stream functions and a simple type discipline to separate deterministic and probabilistic expressions.  ...  Probabilistic programming languages are used to describe probabilistic models and automatically infer distributions of latent (i.e., unobserved) parameters from observations.  ... 
doi:10.1145/3385412.3386009 dblp:conf/pldi/BaudartMASPC20 fatcat:eo67nukmj5brddngglkxaslt4i

Reactive Probabilistic Programming [article]

Guillaume Baudart, Louis Mandel, Eric Atkinson, Benjamin Sherman, Marc Pouzet, Michael Carbin
2020 arXiv   pre-print
We also redesign the delayed sampling inference algorithm to provide efficient streaming inference.  ...  We propose a measure-theoretic semantics of probabilistic stream functions and a simple type discipline to separate deterministic and probabilistic expressions.  ...  Probabilistic programming languages are used to describe probabilistic models and automatically infer distributions of latent (i.e., unobserved) parameters from observations.  ... 
arXiv:1908.07563v2 fatcat:5luwz52gprbqdcceqy7kbz5oxy

miniKanren as a Tool for Symbolic Computation in Python [article]

Brandon T. Willard
2020 arXiv   pre-print
We also discuss the relevance and potential of relational programming for implementing more robust, portable, domain-specific "math-level" optimizations--with a slight focus on Bayesian modeling.  ...  Finally, we describe the work going forward and raise some questions regarding potential cross-overs between statistical modeling and programming language theory.  ...  ACKNOWLEDGMENTS e author would like to thank Jason Hemann and William Byrd for their invaluable input and inspiring work.  ... 
arXiv:2005.11644v3 fatcat:zvjqdgw2pndhvahgz2e6iyvihm

Learning and inferring transportation routines

Lin Liao, Donald J. Patterson, Dieter Fox, Henry Kautz
2007 Artificial Intelligence  
To achieve efficient inference, we apply Rao-Blackwellized particle filters at multiple levels of the model hierarchy.  ...  The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user's destination and mode of transportation.  ...  , Office of Naval Research grant N00014-02-1-0932, DARPA's SDR and ASSIST Programs (grant numbers NBCHC020073 and NBCH-C-05-0137), and Intel Corporation.  ... 
doi:10.1016/j.artint.2007.01.006 fatcat:uqiehnv3jbeqrfs3b4txphzgbq

Conditional independence by typing [article]

Maria I. Gorinova, Andrew D. Gordon, Charles Sutton, Matthijs Vakar
2020 arXiv   pre-print
We present an information flow type system for probabilistic programming that captures conditional independence (CI) relationships, and show that, for a well-typed program in our system, the distribution  ...  A central goal of probabilistic programming languages (PPLs) is to separate modelling from inference. However, this goal is hard to achieve in practice.  ...  University of Edinburgh.  ... 
arXiv:2010.11887v1 fatcat:faez77gfp5e5rfdny4inpz4jva

Tempo tracking and rhythm quantization by sequential Monte Carlo

Ali Taylan Cemgil, Bert Kappen
2001 Neural Information Processing Systems  
For this purpose, we have derived a novel Viterbi algorithm for Rao-Blackwellized particle filters, where a subset of the hidden variables is integrated out.  ...  The resulting model is suitable for realtime tempo tracking and transcription and hence useful in a number of music applications such as adaptive automatic accompaniment and score typesetting.  ...  Acknowledgements This research is supported by the Technology Foundation STW, applied science division of NWO and the technology programme of the Dutch Ministry of Economic Affairs.  ... 
dblp:conf/nips/CemgilK01 fatcat:xycbezjl6fdmdb5upagmyufqei

Contour Grouping Based on Contour-Skeleton Duality

Nagesh Adluru, Longin Jan Latecki
2009 International Journal of Computer Vision  
Hence we adapt the state-of-theart probabilistic framework namely Rao-Blackwellized particle filtering that has been successfully applied to SLAM.  ...  Casting the grouping problem in this manner makes it similar to the problem of Simultaneous Localization and Mapping (SLAM).  ...  Acknowledgements We thank the anonymous reviewers for very insightful and constructive comments that helped to improve several aspects of our paper.  ... 
doi:10.1007/s11263-009-0208-2 fatcat:qf4wpqxqevahnhm42udtptfaqa

Program Analysis of Probabilistic Programs [article]

Maria I. Gorinova
2022 arXiv   pre-print
While substantial work has been done both to formalise probabilistic programming and to improve efficiency of inference, there has been little work that makes use of the available program structure, by  ...  This dissertation presents three novel techniques (both static and dynamic), which aim to improve probabilistic programming using program analysis.  ...  Their method corresponds to automatic variable elimination and, more generally, automatic Rao-Blackwellization.  ... 
arXiv:2204.06868v1 fatcat:2dbonwruuzaopil4aijdeuz4mi

Table of contents

2006 Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006.  
Little Rao-Blackwellized Particle Filtering for 6-DOF Estimation of Attitude and Position via GPS and Inertial Sensors . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Federico . . . . . . . . . . . . . . . . 803 Zoran Zivkovic, Bram Bakker, Ben Kröse A Rao-Blackwellized Particle Filter for Topological Mapping . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  . . . . . . . . . . . . . . . . . . . . . . . . . 2627 Luis Falcón-Morales, Eduardo Bayro-Corrochano Automatic Generation of Contact State Graphs Based on Curvature Monotonic Segmentation .  ... 
doi:10.1109/robot.2006.1641151 fatcat:f5zhr6x7trhazlcmsvfdhkpqm4

2007 Index IEEE Transactions on Automatic Control Vol. 52

2007 IEEE Transactions on Automatic Control  
., and Berman, N., H Control and Estimation of Retarded State-Multiplicative Stochastic Systems; TAC Sept. 1773Sept.  ...  ., and Pappas, G.  ...  ., +, TAC Sept. 2007 1742-1748 Importance sampling Identification and Adaptive Control of Change-Point ARX Models Via Rao- Blackwellized Particle Filters.  ... 
doi:10.1109/tac.2007.913948 fatcat:vpztpth7jnhk7b5o5bt2nyrrdm
« Previous Showing results 1 — 15 out of 138 results