Now showing items 11-14 of 14
Implementation of Dasher, an information efficient input mechanism
Dasher is a novel information efficient text entry system using a language model to offer predictions to the user without constraining the range of words which can be written. In this paper, we discuss the implementation ...
Note on rejection sampling and exact sampling with the Metropolised independence sampler
This short note shows a close relationship between standard rejection sampling and exact sampling by coupling from the past applied to a Metropolised independence sampler. I now know that this idea, first presented as a ...
MCMC for doubly-intractable distributions
Markov Chain Monte Carlo (MCMC) algorithms are routinely used to draw samples from distributions with intractable normalization constants. However, standard MCMC algorithms do not apply to doubly-intractable distributions ...
Gaussian processes and fast matrix-vector multiplies
(Numerical Mathematics in Machine Learning Workshop - International Conference on Machine Learning ICML 2009, 2009)
Gaussian processes (GPs) provide a flexible framework for probabilistic regression. The necessary computations involve standard matrix operations. There have been several attempts to accelerate these operations based on ...