MCMC using Hamiltonian dynamics

RM Neal - arxiv preprint arxiv:1206.1901, 2012 - arxiv.org
Hamiltonian dynamics can be used to produce distant proposals for the Metropolis
algorithm, thereby avoiding the slow exploration of the state space that results from the …

An overview of informed audio source separation

A Liutkus, JL Durrieu, L Daudet… - 2013 14th International …, 2013 - ieeexplore.ieee.org
Audio source separation consists in recovering different unknown signals called sources by
filtering their observed mixtures. In music processing, most mixtures are stereophonic songs …

Backward simulation methods for Monte Carlo statistical inference

F Lindsten, TB Schön - Foundations and Trends® in Machine …, 2013 - nowpublishers.com
Monte Carlo methods, in particular those based on Markov chains and on interacting particle
systems, are by now tools that are routinely used in machine learning. These methods have …

Kernelized Bayesian matrix factorization

M Gönen, S Khan, S Kaski - International conference on …, 2013 - proceedings.mlr.press
We extend kernelized matrix factorization with a fully Bayesian treatment and with an ability
to work with multiple side information sources expressed as different kernels. Kernel …

Bayesian warped Gaussian processes

M Lázaro-Gredilla - Advances in Neural Information …, 2012 - proceedings.neurips.cc
Abstract Warped Gaussian processes (WGP)[1] model output observations in regression
tasks as a parametric nonlinear transformation of a Gaussian process (GP). The use of this …

Unsupervised post-nonlinear unmixing of hyperspectral images using a Hamiltonian Monte Carlo algorithm

Y Altmann, N Dobigeon… - IEEE Transactions on …, 2014 - ieeexplore.ieee.org
This paper presents a nonlinear mixing model for hyperspectral image unmixing. The
proposed model assumes that the pixel reflectances are post-nonlinear functions of …

Variational Gaussian-process factor analysis for modeling spatio-temporal data

J Luttinen, A Ilin - Advances in neural information …, 2009 - proceedings.neurips.cc
We present a probabilistic latent factor model which can be used for studying spatio-
temporal datasets. The spatial and temporal structure is modeled by using Gaussian …

Improving quadrature for constrained integrands

HR Chai, R Garnett - The 22nd International Conference on …, 2019 - proceedings.mlr.press
We present an improved Bayesian framework for performing inference of affine
transformations of constrained functions. We focus on quadrature with nonnegative …

Sampling from a multivariate Gaussian distribution truncated on a simplex: a review

Y Altmann, S McLaughlin… - 2014 IEEE Workshop on …, 2014 - ieeexplore.ieee.org
In many Bayesian models, the posterior distribution of interest is a multivariate Gaussian
distribution restricted to a specific domain. In particular, when the unknown parameters to be …

Identifying targets of multiple co-regulating transcription factors from expression time-series by Bayesian model comparison

MK Titsias, A Honkela, ND Lawrence, M Rattray - BMC systems biology, 2012 - Springer
Background Complete transcriptional regulatory network inference is a huge challenge
because of the complexity of the network and sparsity of available data. One approach to …