We introduce Mean-for-Mode estimation, a variant of an uncollapsed Gibbs sampler that we use to train LDA on a GPU. The algorithm combines benefits of both uncollapsed and collapsed Gibbs samplers. Like a collapsed Gibbs sampler — and unlike an uncollapsed Gibbs sampler — it has good statistical performance, and can use sampling complexity reduction techniques such as sparsity. Meanwhile, like ...

We present a sequential Monte Carlo sampler variant of the partial rejection control algorithm introduced by Liu (2001), termed SMC sampler PRC, and show that this variant can be considered under the same framework of the sequential Monte Carlo sampler of Del Moral et al. (2006). We make connections with existing algorithms and theoretical results, and extend some theoretical results to the SMC...

The performance of two thoracic samplers, the GK2.69 cyclone and the CATHIA-T sampler, and the GK3.51 cyclone was investigated in the field against the standard cowled sampler (current NIOSH 7400 method) to determine the effect of thoracic sampling. The CATHIA-T sampler and the GK2.69 cyclone were operated at 7 and 1.6 l min(-1), respectively. The GK3.51 sampler is related to the GK2.69 cyclone...

This paper describes an efficient sampler for synchronous grammar induction under a nonparametric Bayesian prior. Inspired by ideas from slice sampling, our sampler is able to draw samples from the posterior distributions of models for which the standard dynamic programing based sampler proves intractable on non-trivial corpora. We compare our sampler to a previously proposed Gibbs sampler and ...

This article compares the collection characteristics of a new rotating impactor Florida Latham Bonds (FLB) sampler for ultrafine aerosols with a mimic of the industry standard (Hock-type). The volume and droplet-size distribution collected by the rotating impactors were measured via spectroscopy and microscopy. The rotary impactors were colocated with an isokinetic air sampler for a total volum...

We consider a Gibbs sampler applied to the uniform distribution on a bounded region R ⊆ R. We show that the convergence properties of the Gibbs sampler depend greatly on the smoothness of the boundary of R. Indeed, for sufficiently smooth boundaries the sampler is uniformly ergodic, while for jagged boundaries the sampler could fail to even be geometrically ergodic.

We consider a Gibbs sampler applied to the uniform distribution on a bounded region R R d. We show that the convergence properties of the Gibbs sampler depend greatly on the smoothness of the boundary of R. Indeed, for suuciently smooth boundaries the sampler is uniformly ergodic, while for jagged boundaries the sampler could fail to even be geometrically ergodic.

There are currently no appropriate methods for measuring dermal exposure to volatile agents. To address this we have produced a prototype Institute of Occupational Medicine (IOM) dermal sampler consisting of an adsorbent sandwiched between a permeable membrane and an impervious backing. The concentration of solvent on the membrane surface may be estimated from the mass collected on the adsorben...

This paper proposes and compares two new sampling schemes for sparse deconvolution using a Bernoulli-Gaussian model. To tackle such a deconvolution problem in a blind and unsupervised context, the Markov Chain Monte Carlo (MCMC) framework is usually adopted, and the chosen sampling scheme is most often the Gibbs sampler. However, such a sampling scheme fails to explore the state space efficient...