Time-efficient Bayesian Inference for a (Skewed) Von Mises Distribution on the Torus in a Deep Probabilistic Programming Language

Probabilistic programming languages aid developers performing Bayesian inference. These languages provide programming constructs and tools for probabilistic modeling and automated inference. Prior work introduced a probabilistic programming language, ProbZelus, to extend probabilistic programming functionality to unbounded streams of data. This work demonstrated that the delayed sampling inference algorithm could be extended to work in a streaming context. ProbZelus showed that while delayed sampling could be effectively deployed on some programs, depending on the probabilistic model under consideration, delayed sampling is not guaranteed to use a bounded amount of memory over the course of the execution of the program. In this paper, we the present conditions on a probabilistic program’s execution under which delayed sampling will execute in bounded memory. The two conditions are dataflow properties of the core operations of delayed sampling: the m -consumed property and the unseparated paths property . A program executes in bounded memory under delayed sampling if, and only if, it satisfies the m -consumed and unseparated paths properties. We propose a static analysis that abstracts over these properties to soundly ensure that any program that passes the analysis satisfies these properties, and thus executes in bounded memory under delayed sampling.

Download Full-text

Estimating Ground-Motion Models via Bayesian Inference using Stan

10.31224/osf.io/uj749 ◽

2021 ◽

Author(s):

Nicolas Kuehn ◽

Peter Stafford

Keyword(s):

Bayesian Inference ◽

Ground Motion ◽

Programming Language ◽

Motion Model ◽

Probabilistic Programming ◽

Motion Models ◽

Ground Motion Model ◽

Computer Environment ◽

Ground Motion Models

We provide a simple introduction to the estimation of ground-motion models via Bayesian inference and the probabilistic programming language Stan.We show one ca implement a simple ground-motion model in Stan, and how can run the program from the computer environment R.We also show how one can access the results, and plot summaries of estimated parameters.A large number of different Stan models for the development https://github.com/pstafford/StanGMMTutorial.

Download Full-text

An extension of the von mises distribution

Communication in Statistics- Theory and Methods ◽

10.1080/03610928208828342 ◽

1982 ◽

Vol 11 (15) ◽

pp. 1695-1706 ◽

Cited By ~ 23

Author(s):

E.A. Yfantis ◽

L.E. Borgman

Keyword(s):

Von Mises Distribution ◽

Von Mises

Download Full-text

Error-in-variables model of Malacca wind direction data with the von Mises distribution in southwest monsoon

Applied Mathematical Sciences ◽

10.12988/ams.2021.914521 ◽

2021 ◽

Vol 15 (9) ◽

pp. 471-479

Author(s):

Nurkhairany Amyra Mokhtar ◽

Basri Badyalina ◽

Kerk Lee Chang ◽

Fatin Farazh Ya'acob ◽

Ahmad Faiz Ghazali ◽

...

Keyword(s):

Wind Direction ◽

Southwest Monsoon ◽

Von Mises Distribution ◽

Error In Variables ◽

Von Mises

Download Full-text

STATISTICAL MODEL FOR THE RELATIONSHIP BETWEEN MAIZE KERNEL ORIENTATION AND SEED LEAF AZIMUTH

Experimental Agriculture ◽

10.1017/s0014479715000149 ◽

2015 ◽

Vol 52 (3) ◽

pp. 359-370

Author(s):

ADRIAN KOLLER ◽

GUILHERME TORRES ◽

MICHAEL BUSER ◽

RANDY TAYLOR ◽

BILL RAUN ◽

...

Keyword(s):

Simulation Models ◽

Circular Statistics ◽

Von Mises Distribution ◽

Canopy Closure ◽

Canopy Architecture ◽

Maize Kernel ◽

Angular Data ◽

Significant Yield ◽

Von Mises ◽

The Relationship

SUMMARYHand-planted plots of across-row-oriented corn seeds (Zeamays L.) produce highly structured leaf canopies and have shown significant yield advantage over randomly planted plots in prior studies. For further investigation of the phenomenon by simulation, the objective of this study was to develop a probabilistic model for the correlation between seed orientation and initial plant orientation. In greenhouse trials, the azimuthal orientation of kernels of four different hybrids was recorded at planting. At collar setting of the seed leaf, the orientation of the seed leaf was determined and the angular data subjected to the analytical methods of circular statistics. The results indicate that the correlation between seed azimuth and seed leaf azimuth can be described by a von Mises distribution. The probabilistic seed to seed leaf azimuth model described herein may be implemented in simulation models to investigate the effect of canopy architecture, canopy closure and light interception efficiency of corn under conditions of seed oriented planting.

Download Full-text