Approximate Bayesian techniques for inference in stochastic dynamical systems

This thesis is concerned with approximate inference in dynamical systems, from a variational Bayesian perspective. When modelling real world dynamical systems, stochastic differential equations appear as a natural choice, mainly because of their ability to model the noise of the system by adding a variant of some stochastic process to the deterministic dynamics. Hence, inference in such processes has drawn much attention. Here two new extended frameworks are derived and presented that are based on basis function expansions and local polynomial approximations of a recently proposed variational Bayesian algorithm. It is shown that the new extensions converge to the original variational algorithm and can be used for state estimation (smoothing). However, the main focus is on estimating the (hyper-) parameters of these systems (i.e. drift parameters and diffusion coefficients). The new methods are numerically validated on a range of different systems which vary in dimensionality and non-linearity. These are the Ornstein-Uhlenbeck process, for which the exact likelihood can be computed analytically, the univariate and highly non-linear, stochastic double well and the multivariate chaotic stochastic Lorenz '63 (3-dimensional model). The algorithms are also applied to the 40 dimensional stochastic Lorenz '96 system. In this investigation these new approaches are compared with a variety of other well known methods such as the ensemble Kalman filter / smoother, a hybrid Monte Carlo sampler, the dual unscented Kalman filter (for jointly estimating the systems states and model parameters) and full weak-constraint 4D-Var. Empirical analysis of their asymptotic behaviour as a function of observation density or length of time window increases is provided.

A comparison of variational and Markov chain Monte Carlo methods for inference in partially observed stochastic dynamic systems

In recent work we have developed a novel variational inference method for partially observed systems governed by stochastic differential equations. In this paper we provide a comparison of the Variational Gaussian Process Smoother with an exact solution computed using a Hybrid Monte Carlo approach to path sampling, applied to a stochastic double well potential model. It is demonstrated that the variational smoother provides us a very accurate estimate of mean path while conditional variance is slightly underestimated. We conclude with some remarks as to the advantages and disadvantages of the variational smoother. © 2008 Springer Science + Business Media LLC.

Gaussian process approximations of stochastic differential equations

Stochastic differential equations arise naturally in a range of contexts, from financial to environmental modeling. Current solution methods are limited in their representation of the posterior process in the presence of data. In this work, we present a novel Gaussian process approximation to the posterior measure over paths for a general class of stochastic differential equations in the presence of observations. The method is applied to two simple problems: the Ornstein-Uhlenbeck process, of which the exact solution is known and can be compared to, and the double-well system, for which standard approaches such as the ensemble Kalman smoother fail to provide a satisfactory result. Experiments show that our variational approximation is viable and that the results are very promising as the variational approximate solution outperforms standard Gaussian process regression for non-Gaussian Markov processes.

Finitely coordinated models for low-temperature phases of amorphous systems

We introduce models of heterogeneous systems with finite connectivity defined on random graphs to capture finite-coordination effects on the low-temperature behaviour of finite-dimensional systems. Our models use a description in terms of small deviations of particle coordinates from a set of reference positions, particularly appropriate for the description of low-temperature phenomena. A Born-von Karman-type expansion with random coefficients is used to model effects of frozen heterogeneities. The key quantity appearing in the theoretical description is a full distribution of effective single-site potentials which needs to be determined self-consistently. If microscopic interactions are harmonic, the effective single-site potentials turn out to be harmonic as well, and the distribution of these single-site potentials is equivalent to a distribution of localization lengths used earlier in the description of chemical gels. For structural glasses characterized by frustration and anharmonicities in the microscopic interactions, the distribution of single-site potentials involves anharmonicities of all orders, and both single-well and double-well potentials are observed, the latter with a broad spectrum of barrier heights. The appearance of glassy phases at low temperatures is marked by the appearance of asymmetries in the distribution of single-site potentials, as previously observed for fully connected systems. Double-well potentials with a broad spectrum of barrier heights and asymmetries would give rise to the well-known universal glassy low-temperature anomalies when quantum effects are taken into account. © 2007 IOP Publishing Ltd.

Variational Markov Chain Monte Carlo for Bayesian smoothing of non-linear niffusions

In this paper we develop set of novel Markov chain Monte Carlo algorithms for Bayesian smoothing of partially observed non-linear diffusion processes. The sampling algorithms developed herein use a deterministic approximation to the posterior distribution over paths as the proposal distribution for a mixture of an independence and a random walk sampler. The approximating distribution is sampled by simulating an optimized time-dependent linear diffusion process derived from the recently developed variational Gaussian process approximation method. Flexible blocking strategies are introduced to further improve mixing, and thus the efficiency, of the sampling algorithms. The algorithms are tested on two diffusion processes: one with double-well potential drift and another with SINE drift. The new algorithm's accuracy and efficiency is compared with state-of-the-art hybrid Monte Carlo based path sampling. It is shown that in practical, finite sample, applications the algorithm is accurate except in the presence of large observation errors and low observation densities, which lead to a multi-modal structure in the posterior distribution over paths. More importantly, the variational approximation assisted sampling algorithm outperforms hybrid Monte Carlo in terms of computational efficiency, except when the diffusion process is densely observed with small errors in which case both algorithms are equally efficient.

Estimating parameters in stochastic systems:a variational Bayesian approach

This work is concerned with approximate inference in dynamical systems, from a variational Bayesian perspective. When modelling real world dynamical systems, stochastic differential equations appear as a natural choice, mainly because of their ability to model the noise of the system by adding a variation of some stochastic process to the deterministic dynamics. Hence, inference in such processes has drawn much attention. Here a new extended framework is derived that is based on a local polynomial approximation of a recently proposed variational Bayesian algorithm. The paper begins by showing that the new extension of this variational algorithm can be used for state estimation (smoothing) and converges to the original algorithm. However, the main focus is on estimating the (hyper-) parameters of these systems (i.e. drift parameters and diffusion coefficients). The new approach is validated on a range of different systems which vary in dimensionality and non-linearity. These are the Ornstein–Uhlenbeck process, the exact likelihood of which can be computed analytically, the univariate and highly non-linear, stochastic double well and the multivariate chaotic stochastic Lorenz ’63 (3D model). As a special case the algorithm is also applied to the 40 dimensional stochastic Lorenz ’96 system. In our investigation we compare this new approach with a variety of other well known methods, such as the hybrid Monte Carlo, dual unscented Kalman filter, full weak-constraint 4D-Var algorithm and analyse empirically their asymptotic behaviour as a function of observation density or length of time window increases. In particular we show that we are able to estimate parameters in both the drift (deterministic) and the diffusion (stochastic) part of the model evolution equations using our new methods.

A new variational radial basis function approximation for inference in multivariate diffusions

In this paper we present a radial basis function based extension to a recently proposed variational algorithm for approximate inference for diffusion processes. Inference, for state and in particular (hyper-) parameters, in diffusion processes is a challenging and crucial task. We show that the new radial basis function approximation based algorithm converges to the original algorithm and has beneficial characteristics when estimating (hyper-)parameters. We validate our new approach on a nonlinear double well potential dynamical system.

Variational Markov chain Monte Carlo for Bayesian smoothing of non-linear diffusions

In this paper we develop set of novel Markov Chain Monte Carlo algorithms for Bayesian smoothing of partially observed non-linear diffusion processes. The sampling algorithms developed herein use a deterministic approximation to the posterior distribution over paths as the proposal distribution for a mixture of an independence and a random walk sampler. The approximating distribution is sampled by simulating an optimized time-dependent linear diffusion process derived from the recently developed variational Gaussian process approximation method. The novel diffusion bridge proposal derived from the variational approximation allows the use of a flexible blocking strategy that further improves mixing, and thus the efficiency, of the sampling algorithms. The algorithms are tested on two diffusion processes: one with double-well potential drift and another with SINE drift. The new algorithm's accuracy and efficiency is compared with state-of-the-art hybrid Monte Carlo based path sampling. It is shown that in practical, finite sample applications the algorithm is accurate except in the presence of large observation errors and low to a multi-modal structure in the posterior distribution over paths. More importantly, the variational approximation assisted sampling algorithm outperforms hybrid Monte Carlo in terms of computational efficiency, except when the diffusion process is densely observed with small errors in which case both algorithms are equally efficient. © 2011 Springer-Verlag.

Double-blind, placebo-controlled, randomized study of eicosapentaenoic acid diester in patients with cancer cachexia

Purpose: Eicosapentaenoic acid (EPA) has been proposed to have specific anticachectic effects. This trial compared EPA diethyl ester with placebo in cachectic cancer patients for effects on weight and lean body mass. Patients and Methods: Five hundred eighteen weight-losing patients with advanced gastrointestinal or lung cancer were studied in a multicenter, double-blind, placebo controlled trial. Patients were randomly assigned to receive a novel preparation of pure EPA at a dose of 2 g or 4 g daily or placebo (2g EPA, n = 175; 4 g EPA, n = 172; placebo, n = 171). Patients were assessed at 4 weeks and 8 weeks. Results: The groups were well balanced at baseline. Mean weight loss at baseline was 18% (n = 518). Over the 8-week treatment period, both intention-to-treat analysis and per protocol analysis revealed no statistically significant improvements in survival, weight, or other nutritional variables. There was, however, a trend in favor of EPA with analysis of the primary end point, weight, at 8 weeks showing a borderline, nonsignificant treatment effect (P = .066). Relative to placebo, mean weight increased by 1.2 kg with 2 g EPA (95% CI, 0 kg to 2.3 kg) and by 0.3 kg with 4g EPA (-0.9 kg to 1.5 kg). Conclusion: The results indicate no statistically significant benefit from single agent EPA in the treatment of cancer cachexia. Future studies should concentrate on other agents or combination regimens. © 2006 by American Society of Clinical Oncology.

Apodisation of photo-induced waveguide gratings using double-exposure with complementary duty cycles

We present a novel apodisation scheme for photo-induced waveguide gratings. The apodisation is implemented with double exposures that have reversely varying duty cycles. We have successfully applied the proposed scheme to remove the sidelobes of long period gratings (LPGs). We also observed for the first time super strong sidelobes in LPGs when creating them with only a single varying-duty-cycle exposure. The strong sidelobes can be well explained with a Mach-Zehnder interference model.

Optimization of chemical plant simulation using double collocation

A method has been constructed for the solution of a wide range of chemical plant simulation models including differential equations and optimization. Double orthogonal collocation on finite elements is applied to convert the model into an NLP problem that is solved either by the VF 13AD package based on successive quadratic programming, or by the GRG2 package, based on the generalized reduced gradient method. This approach is termed simultaneous optimization and solution strategy. The objective functional can contain integral terms. The state and control variables can have time delays. Equalities and inequalities containing state and control variables can be included into the model as well as algebraic equations and inequalities. The maximum number of independent variables is 2. Problems containing 3 independent variables can be transformed into problems having 2 independent variables using finite differencing. The maximum number of NLP variables and constraints is 1500. The method is also suitable for solving ordinary and partial differential equations. The state functions are approximated by a linear combination of Lagrange interpolation polynomials. The control function can either be approximated by a linear combination of Lagrange interpolation polynomials or by a piecewise constant function over finite elements. The number of internal collocation points can vary by finite elements. The residual error is evaluated at arbitrarily chosen equidistant grid-points, thus enabling the user to check the accuracy of the solution between collocation points, where the solution is exact. The solution functions can be tabulated. There is an option to use control vector parameterization to solve optimization problems containing initial value ordinary differential equations. When there are many differential equations or the upper integration limit should be selected optimally then this approach should be used. The portability of the package has been addressed converting the package from V AX FORTRAN 77 into IBM PC FORTRAN 77 and into SUN SPARC 2000 FORTRAN 77. Computer runs have shown that the method can reproduce optimization problems published in the literature. The GRG2 and the VF I 3AD packages, integrated into the optimization package, proved to be robust and reliable. The package contains an executive module, a module performing control vector parameterization and 2 nonlinear problem solver modules, GRG2 and VF I 3AD. There is a stand-alone module that converts the differential-algebraic optimization problem into a nonlinear programming problem.

Apodisation of photo-induced waveguide gratings using double-exposure with complementary duty cycles

We present a novel apodisation scheme for photo-induced waveguide gratings. The apodisation is implemented with double exposures that have reversely varying duty cycles. We have successfully applied the proposed scheme to remove the sidelobes of long period gratings (LPGs). We also observed for the first time super strong sidelobes in LPGs when creating them with only a single varying-duty-cycle exposure. The strong sidelobes can be well explained with a Mach-Zehnder interference model.

'It's a double-edged thing':the paradox of civil partnership and why some couples are choosing not to have one

Since their introduction in 2005, thousands of same-sex couples in the UK have had a civil partnership. However, many other couples have chosen not to have one. This qualitative study explores why some same-sex couples are choosing not to have a civil partnership. Seven semi-structured interviews were conducted with 12 people (five couples and two individuals) who identified as lesbian, gay or bisexual, and analysed using discourse analysis. Participants' accounts were characterised by ambivalence about civil partnership, and three main paradoxes were identified: the 'good but not good enough' paradox, the 'unwanted prize' paradox and the 'legal rights v. social oppression paradox. A major source of ambivalence was support for rights but resistance to assimilation into dominant heteronormative cultural frameworks. Participants negotiated this ambivalence in a variety of ways, including considering how to have a civil partnership that is different from 'marriage', and adopting a pragmatic position. The analysis highlights the importance of social recognition and support for a range of relationship forms and identities, as well as for an ongoing critical debate about civil partnerships and same-sex marriage. © The Author(s) 2011.

Spectrum redistribution for cognitive radios using discriminatory spectrum double auction

With the reformation of spectrum policy and the development of cognitive radio, secondary users will be allowed to access spectrums licensed to primary users. Spectrum auctions can facilitate this secondary spectrum access in a market-driven way. To design an efficient auction framework, we first study the supply and demand pressures and the competitive equilibrium of the secondary spectrum market, considering the spectrum reusability. In well-designed auctions, competition among participants should lead to the competitive equilibrium according to the traditional economic point of view. Then, a discriminatory price spectrum double auction framework is proposed for this market. In this framework, rational participants compete with each other by using bidding prices, and their profits are guaranteed to be non-negative. A near-optimal heuristic algorithm is also proposed to solve the auction clearing problem of the proposed framework efficiently. Experimental results verify the efficiency of the proposed auction clearing algorithm and demonstrate that competition among secondary users and primary users can lead to the competitive equilibrium during auction iterations using the proposed auction framework. Copyright © 2011 John Wiley & Sons, Ltd.

A double-blind randomized study comparing the effects of continuing or not continuing rosiglitazone + metformin therapy when starting insulin therapy in people with type 2 diabetes

Aims: To compare the efficacy and safety of either continuing or discontinuing rosiglitazone + metformin fixed-dose combination when starting insulin therapy in people with Type 2 diabetes inadequately controlled on oral therapy. Methods: In this 24-week double-blind study, 324 individuals with Type 2 diabetes inadequately controlled on maximum dose rosiglitazone + metformin therapy were randomly assigned to twice-daily premix insulin therapy (target pre-breakfast and pre-evening meal glucose ≤ 6.5 mmol/l) in addition to either rosiglitazone + metformin (8/2000 mg) or placebo. Results: Insulin dose at week 24 was significantly lower with rosiglitazone + metformin (33.5 ± 1.5 U/day, mean ± se) compared with placebo [59.0 ± 3.0 U/day; model-adjusted difference -26.6 (95% CI -37.7, -15,5) U/day, P < 0.001]. Despite this, there was greater improvement in glycaemic control [HbA 1c rosiglitazone + metformin vs. placebo 6.8 ± 0.1 vs. 7.5 ± 0.1%; difference -0.7 (-0.8, -0.5)%, P < 0.001] and more individuals achieved glycaemic targets (HbA1c < 7.0% 70 vs. 34%, P < 0.001). The proportion of individuals reporting at least one hypoglycaemic event during the last 12 weeks of treatment was similar in the two groups (rosiglitazone + metformin vs. placebo 25 vs. 27%). People receiving rosiglitazone + metformin in addition to insulin reported greater treatment satisfaction than those receiving insulin alone. Both treatment regimens were well tolerated but more participants had oedema [12 (7%) vs. 4 (3%)] and there was more weight gain [3.7 vs. 2.6 kg; difference 1.1 (0.2, 2.1) kg, P = 0.02] with rosiglitazone + metformin. Conclusions: Addition of insulin to rosiglitazone + metformin enabled more people to reach glycaemic targets with less insulin, and was generally well tolerated. © 2007 The Authors.