Gaussian process volatility model

The prediction of time-changing variances is an important task in the modeling of financial data. Standard econometric models are often limited as they assume rigid functional relationships for the evolution of the variance. Moreover, functional parameters are usually learned by maximum likelihood, which can lead to over-fitting. To address these problems we introduce GP-Vol, a novel non-parametric model for time-changing variances based on Gaussian Processes. This new model can capture highly flexible functional relationships for the variances. Furthermore, we introduce a new online algorithm for fast inference in GP-Vol. This method is much faster than current offline inference procedures and it avoids overfitting problems by following a fully Bayesian approach. Experiments with financial data show that GP-Vol performs significantly better than current standard alternatives.

Student-t processes as alternatives to Gaussian processes

We investigate the Student-t process as an alternative to the Gaussian process as a non-parametric prior over functions. We derive closed form expressions for the marginal likelihood and predictive distribution of a Student-t process, by integrating away an inverse Wishart process prior over the co-variance kernel of a Gaussian process model. We show surprising equivalences between different hierarchical Gaussian process models leading to Student-t processes, and derive a new sampling scheme for the inverse Wishart process, which helps elucidate these equivalences. Overall, we show that a Student-t process can retain the attractive properties of a Gaussian process - a nonparamet-ric representation, analytic marginal and predictive distributions, and easy model selection through covariance kernels - but has enhanced flexibility, and predictive covariances that, unlike a Gaussian process, explicitly depend on the values of training observations. We verify empirically that a Student-t process is especially useful in situations where there are changes in covariance structure, or in applications such as Bayesian optimization, where accurate predictive covariances are critical for good performance. These advantages come at no additional computational cost over Gaussian processes.

Calibrating the Gaussian multi-target tracking model

We present novel batch and online (sequential) versions of the expectation-maximisation (EM) algorithm for inferring the static parameters of a multiple target tracking (MTT) model. Online EM is of particular interest as it is a more practical method for long data sets since in batch EM, or a full Bayesian approach, a complete browse of the data is required between successive parameter updates. Online EM is also suited to MTT applications that demand real-time processing of the data. Performance is assessed in numerical examples using simulated data for various scenarios. For batch estimation our method significantly outperforms an existing gradient based maximum likelihood technique, which we show to be significantly biased. © 2014 Springer Science+Business Media New York.

Symmetrical 2-D hermite-gaussian square launch for high bit rate transmission in multimode fiber links

A 2-D Hermite-Gaussian square launch is demonstrated to show improved systems capacity over multimode fiber links. It shows a bandwidth improvement over both center and offset launches and exhibits ±5 ìm misalignment tolerance. © OSA/OFC/NFOEC 2011.

Fault tolerant control using Gaussian processes and model predictive control

Essential ingredients for fault-tolerant control are the ability to represent system behaviour following the occurrence of a fault, and the ability to exploit this representation for deciding control actions. Gaussian processes seem to be very promising candidates for the first of these, and model predictive control has a proven capability for the second. We therefore propose to use the two together to obtain fault-tolerant control functionality. Our proposal is illustrated by several reasonably realistic examples drawn from flight control. © 2013 IEEE.

First principles interatomic potential for tungsten based on Gaussian process regression

An accurate description of atomic interactions, such as that provided by first principles quantum mechanics, is fundamental to realistic prediction of the properties that govern plasticity, fracture or crack propagation in metals. However, the computational complexity associated with modern schemes explicitly based on quantum mechanics limits their applications to systems of a few hundreds of atoms at most. This thesis investigates the application of the Gaussian Approximation Potential (GAP) scheme to atomistic modelling of tungsten - a bcc transition metal which exhibits a brittle-to-ductile transition and whose plasticity behaviour is controlled by the properties of $\frac{1}{2} \langle 111 \rangle$ screw dislocations. We apply Gaussian process regression to interpolate the quantum-mechanical (QM) potential energy surface from a set of points in atomic configuration space. Our training data is based on QM information that is computed directly using density functional theory (DFT). To perform the fitting, we represent atomic environments using a set of rotationally, permutationally and reflection invariant parameters which act as the independent variables in our equations of non-parametric, non-linear regression. We develop a protocol for generating GAP models capable of describing lattice defects in metals by building a series of interatomic potentials for tungsten. We then demonstrate that a GAP potential based on a Smooth Overlap of Atomic Positions (SOAP) covariance function provides a description of the $\frac{1}{2} \langle 111 \rangle$ screw dislocation that is in agreement with the DFT model. We use this potential to simulate the mobility of $\frac{1}{2} \langle 111 \rangle$ screw dislocations by computing the Peierls barrier and model dislocation-vacancy interactions to QM accuracy in a system containing more than 100,000 atoms.

Effects of electron-electron interactions on the electronic Raman scattering of graphite in high magnetic fields

We report the observation of strongly temperature (T)-dependent spectral lines in electronic Raman-scattering spectra of graphite in a high magnetic field up to 45 T applied along the c axis. The magnetic field quantizes the in-plane motion, while the out-of-plane motion remains free, effectively reducing the system dimension from 3 to 1. Optically created electron-hole pairs interact with, or shake up, the one-dimensional Fermi sea in the lowest Landau subbands. Based on the Tomonaga-Luttinger liquid theory, we show that interaction effects modify the spectral line shape from (ω-Δ)-1/2 to (ω-Δ)2α-1/2 at T = 0. At finite T, we predict a thermal broadening factor that increases linearly with T. Our model reproduces the observed T-dependent line shape, determining the electron-electron interaction parameter α to be ∼0.05 at 40 T. © 2014 American Physical Society.

Gaussian processes for POMDP-based dialogue manager optimization

A partially observable Markov decision process (POMDP) has been proposed as a dialog model that enables automatic optimization of the dialog policy and provides robustness to speech understanding errors. Various approximations allow such a model to be used for building real-world dialog systems. However, they require a large number of dialogs to train the dialog policy and hence they typically rely on the availability of a user simulator. They also require significant designer effort to hand-craft the policy representation. We investigate the use of Gaussian processes (GPs) in policy modeling to overcome these problems. We show that GP policy optimization can be implemented for a real world POMDP dialog manager, and in particular: 1) we examine different formulations of a GP policy to minimize variability in the learning process; 2) we find that the use of GP increases the learning rate by an order of magnitude thereby allowing learning by direct interaction with human users; and 3) we demonstrate that designer effort can be substantially reduced by basing the policy directly on the full belief space thereby avoiding ad hoc feature space modeling. Overall, the GP approach represents an important step forward towards fully automatic dialog policy optimization in real world systems. © 2013 IEEE.

Relationships between the biomass of algal crusts in fields and their compressive strength

In the desert areas of China investigated by the authors, various biological crusts were predominately associated with three blue-green algal (cyano bacterial) species, Microcoleus vaginatus Gom., Phormidium tenue (Menegh.) Gom. and Seytonema javanicum (Mitz.) Born et Flah. Their biomass and their compressive strength were measured simultaneously in the field in this study. It was also found that the compressive strength of algal crusts was enhanced with the increasing of algal biomass from an undetectable level to a value as high as 9.6mg g(-1) dry soil. However, when the algal biomass decreased, the compressive strength did not descend immediately, but remained relatively steady. The higher the algal biomass became, the thicker were the algal crusts formed. Given the same biomass, the highest compressive strength of man-made algal crusts in fields was found at an algal ratio of 62.5% M. vaginatus, 31.25% P. tenue and 6.25% S. javanicum, and it reached 0.89kgcm(-2). When the biomass of the crusts increased above the value of 8.16 mg chl ag(-1) dry soil, the compressive strength would not ascend easily. It indicated that the compressive strength of man-made algal crusts appeared temporarily saturated in the field. (c) 2006 Elsevier Ltd. All rights reserved.

20 Gb/s mode-group-division multiplexing employing Hermite-Gaussian launches over worst-case multimode fiber links

For the first time, mode group division multiplexing is achieved in a multimode fiber link using a 2-D Hermite-Gaussian mode launch. 20 Gb/s error-free transmission is achieved over a 250 m worst-case OM1 multimode fiber link. © OSA 2014.

Modelling and comparison of trapped fields in (RE)BCO bulk superconductors for activation using pulsed field magnetization

The ability to generate a permanent, stable magnetic field unsupported by an electromotive force is fundamental to a variety of engineering applications. Bulk high temperature superconducting (HTS) materials can trap magnetic fields of magnitude over ten times higher than the maximum field produced by conventional magnets, which is limited practically to rather less than 2 T. In this paper, two large c-axis oriented, single-grain YBCO and GdBCO bulk superconductors are magnetized by the pulsed field magnetization (PFM) technique at temperatures of 40 and 65 K and the characteristics of the resulting trapped field profile are investigated with a view of magnetizing such samples as trapped field magnets (TFMs) in situ inside a trapped flux-type superconducting electric machine. A comparison is made between the temperatures at which the pulsed magnetic field is applied and the results have strong implications for the optimum operating temperature for TFMs in trapped flux-type superconducting electric machines. The effects of inhomogeneities, which occur during the growth process of single-grain bulk superconductors, on the trapped field and maximum temperature rise in the sample are modelled numerically using a 3D finite-element model based on the H-formulation and implemented in Comsol Multiphysics 4.3a. The results agree qualitatively with the observed experimental results, in that inhomogeneities act to distort the trapped field profile and reduce the magnitude of the trapped field due to localized heating within the sample and preferential movement and pinning of flux lines around the growth section regions (GSRs) and growth sector boundaries (GSBs), respectively. The modelling framework will allow further investigation of various inhomogeneities that arise during the processing of (RE)BCO bulk superconductors, including inhomogeneous Jc distributions and the presence of current-limiting grain boundaries and cracks, and it can be used to assist optimization of processing and PFM techniques for practical bulk superconductor applications. © 2014 IOP Publishing Ltd.

Bayesian inference and learning in Gaussian process state-space models with Particle MCMC

State-space models are successfully used in many areas of science, engineering and economics to model time series and dynamical systems. We present a fully Bayesian approach to inference and learning (i.e. state estimation and system identification) in nonlinear nonparametric state-space models. We place a Gaussian process prior over the state transition dynamics, resulting in a flexible model able to capture complex dynamical phenomena. To enable efficient inference, we marginalize over the transition dynamics function and, instead, infer directly the joint smoothing distribution using specially tailored Particle Markov Chain Monte Carlo samplers. Once a sample from the smoothing distribution is computed, the state transition predictive distribution can be formulated analytically. Our approach preserves the full nonparametric expressivity of the model and can make use of sparse Gaussian processes to greatly reduce computational complexity.

Classification using log Gaussian Cox processes

McCullagh and Yang (2006) suggest a family of classification algorithms based on Cox processes. We further investigate the log Gaussian variant which has a number of appealing properties. Conditioned on the covariates, the distribution over labels is given by a type of conditional Markov random field. In the supervised case, computation of the predictive probability of a single test point scales linearly with the number of training points and the multiclass generalization is straightforward. We show new links between the supervised method and classical nonparametric methods. We give a detailed analysis of the pairwise graph representable Markov random field, which we use to extend the model to semi-supervised learning problems, and propose an inference method based on graph min-cuts. We give the first experimental analysis on supervised and semi-supervised datasets and show good empirical performance.

Contamination and distribution of polychlorinated dibenzo-p-dioxins and dibenzofurans (PCDD/F) in agriculture fields in Ya-Er Lake area, China

The contamination and distribution of polychlorinated dibeinizo-p-dioxins and dibenzofurans (PCDD/Fs) from two agricultural fields of a heavily polluted lake area in China (Ya-Er Lake) are presented. The vertical distribution pattern of total PCDD/Fs in soil cores reveals that the maximum concentration was in the layer of 20-30 cm. The concentrations in the top layer of soil at the two sites were similar (17.48 ng/kg at Site 1 and 18.10 ng/kg at Site 2), but the maximum concentration of Site 1 (120.8 ng/kg) was two times higher than that of Site 2 (64.39 ng/kg). The maximum concentration of PCDD/Fs in mud cores in rice fields (0-50 cm) at Sites 1 and 2 was in the layer of 0-10 cm. The maximum PCDD/F concentration in the top layer in mud at Site 1 (203.1 ng/kg) was higher than that at Site 2: (143.3 ng/kg). Significant correlations were found between the mind PCDD/Fs and the organic carbon content (R = 0.9743, P< 0,05 at Site 1; R = 0.9821, P< 0.05 at Site 2), the two variables being highly correlated (R = 0.9049, P< 0.05, at Site 1; R = 0.9916, P< 0.05 at Site 2). All correlation coefficients were significant at the 95% level. Concentrations were highly correlated with organic carbon, indicating that sorption to organic carbon was the dominant mechanism. Using principal component analysis, the homologue profiles of soil, mud, and plants (rice and radish) were compared. The PCDD/F patterns in plants were found not to be correlated to those in soil and mud. This suggests that atmospheric deposition may be the main source of PCDD/Fs in rice grain. However, mixed exposure involving uptake mechanisms and atmospheric deposition is considered main the source of PCDD/F pollution in radishes. (C) 2002 Elsevier Science (USA).