English
Related papers

Related papers: Joint Distributions for TensorFlow Probability

200 papers

Probabilistic programming languages and modeling toolkits are two modular ways to build and reuse stochastic models and inference procedures. Combining strengths of both, we express models and inference as generalized coroutines in the same…

Programming Languages · Computer Science 2012-05-14 Oleg Kiselyov , Chung-chieh Shan

A systematic study of the probability distribution of superimposed random codes is presented through the use of generating functions. Special attention is paid to the cases of either uniformly distributed but not necessarily independent or…

Databases · Computer Science 2008-06-19 Bernd Günther

Scaling probabilistic models to large realistic problems and datasets is a key challenge in machine learning. Central to this effort is the development of tractable probabilistic models (TPMs): models whose structure guarantees efficient…

Artificial Intelligence · Computer Science 2020-06-30 Honghua Zhang , Steven Holtzen , Guy Van den Broeck

We study machine learning formulations of inductive program synthesis; given input-output examples, we try to synthesize source code that maps inputs to corresponding outputs. Our aims are to develop new machine learning approaches based on…

Machine Learning · Computer Science 2016-08-17 Alexander L. Gaunt , Marc Brockschmidt , Rishabh Singh , Nate Kushman , Pushmeet Kohli , Jonathan Taylor , Daniel Tarlow

These are lecture notes for various Summer and Winter schools that I have given. The notes describe the methodology called Variational Modelling, and focus on the application to the modelling of gradient-flow systems. I describe the…

Mathematical Physics · Physics 2014-02-11 Mark A. Peletier

Probabilistic inference provides a language for describing how organisms may learn from and adapt to their environment. The computations needed to implement probabilistic inference often require specific representations, akin to having the…

Molecular Networks · Quantitative Biology 2018-06-28 Yarden Katz , Michael Springer , Walter Fontana

Dataflow matrix machines are a powerful generalization of recurrent neural networks. They work with multiple types of arbitrary linear streams, multiple types of powerful neurons, and allow to incorporate higher-order constructions. We…

Neural and Evolutionary Computing · Computer Science 2018-05-29 Michael Bukatin , Steve Matthews , Andrey Radul

A partial differential equation governing the global evolution of the joint probability distribution of an arbitrary number of local flow observations, drawn randomly from a control volume, is derived and applied to examples involving…

Fluid Dynamics · Physics 2026-01-14 John Craske , Paul Mannix

Recursive calls over recursive data are useful for generating probability distributions, and probabilistic programming allows computations over these distributions to be expressed in a modular and intuitive way. Exact inference is also…

Programming Languages · Computer Science 2023-03-28 David Chiang , Colin McDonald , Chung-chieh Shan

We develop a denotational model for probabilistic and concurrent imperative programs, a class of programs with standard control flow via conditionals and while-loops, as well as probabilistic actions and parallel composition. Whereas…

Programming Languages · Computer Science 2025-06-10 Noam Zilberstein , Daniele Gorla , Alexandra Silva

This paper investigates the combinatorics that gives rise to the Boltzmann probability distribution. Despite being one of the most important distributions in physics and other fields of science, the mathematics of the underlying model of…

Probability · Mathematics 2025-07-09 Bart Jacobs

Dense flow visualization is a popular visualization paradigm. Traditionally, the various models and methods in this area use a continuous formulation, resting upon the solid foundation of functional analysis. In this work, we examine a…

Graphics · Computer Science 2020-07-06 Daniel Preuß , Tino Weinkauf , Jens Krüger

We introduce a new type of graphical model called a "cumulative distribution network" (CDN), which expresses a joint cumulative distribution as a product of local functions. Each local function can be viewed as providing evidence about…

Machine Learning · Computer Science 2012-06-18 Jim Huang , Brendan J. Frey

A class of probability distributions is characterized via equalities in law between two order statistics shifted by independent exponential variables. An explicit formula for the quintile function of the identified family of distributions…

Probability · Mathematics 2011-07-26 M. Ahsanullah , V. B. Nevzorov , George P. Yanev

A predictive distribution over a sequence of $N+1$ events is said to be "frequency mimicking" whenever the probability for the final event conditioned on the outcome of the first $N$ events equals the relative frequency of successes among…

Methodology · Statistics 2019-09-06 Frank Lad , Giuseppe Sanfilippo

An expression for the joint probability distribution of the principal curvatures at an arbitrary point in the ensemble of isosurfaces defined on isotropic Gaussian random fields on Rn is derived. The result is obtained by deriving symmetry…

Mathematical Physics · Physics 2007-05-23 Paulo R. S. Mendonca , Rahul Bhotika , James V. Miller

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Computation and Language · Computer Science 2025-03-03 Rachel Wicks , Kartik Ravisankar , Xinchen Yang , Philipp Koehn , Matt Post

This book is a graduate-level introduction to probabilistic programming. It not only provides a thorough background for anyone wishing to use a probabilistic programming system, but also introduces the techniques needed to design and build…

Machine Learning · Statistics 2021-10-20 Jan-Willem van de Meent , Brooks Paige , Hongseok Yang , Frank Wood

The exponential family of models is defined in a general setting, not relying on probability theory. Some results of information geometry are shown to remain valid. Exponential families both of classical and of quantum mechanical…

Mathematical Physics · Physics 2015-06-03 Jan Naudts , Ben Anthonis

The embedding space of language models is widely believed to capture the semantic relationships; for instance, embeddings of digits often exhibit an ordered structure that corresponds to their natural sequence. However, the mechanisms…

Machine Learning · Computer Science 2025-09-25 Junjie Yao , Zhi-Qin John Xu