Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics

We introduce a novel geometry-informed irreversible perturbation that accelerates convergence of the Langevin algorithm for Bayesian computation. It is well documented that there exist perturbations to the Langevin dynamics that preserve its invariant measure while accelerating its convergence. Irreversible perturbations and reversible perturbations (such as Riemannian manifold Langevin dynamics (RMLD)) have separately been shown to improve the performance of Langevin samplers. We consider these two perturbations simultaneously by presenting a novel form of irreversible perturbation for RMLD that is informed by the underlying geometry. Through numerical examples, we show that this new irreversible perturbation can improve estimation performance over irreversible perturbations that do not take the geometry into account. Moreover we demonstrate that irreversible perturbations generally can be implemented in conjunction with the stochastic gradient version of the Langevin algorithm. Lastly, while continuous-time irreversible perturbations cannot impair the performance of a Langevin estimator, the situation can sometimes be more complicated when discretization is considered. To this end, we describe a discrete-time example in which irreversibility increases both the bias and variance of the resulting estimator.

Exploiting network topology for large-scale inference of nonlinear reaction models

The development of chemical reaction models aids understanding and prediction in areas ranging from biology to electrochemistry and combustion. A systematic approach to building reaction network models uses observational data not only to estimate unknown parameters but also to learn model structure. Bayesian inference provides a natural approach to this data-driven construction of models. Yet traditional Bayesian model inference methodologies that numerically evaluate the evidence for each model are often infeasible for nonlinear reaction network inference, as the number of plausible models can be combinatorially large. Alternative approaches based on model-space sampling can enable large-scale network inference, but their realization presents many challenges. In this paper, we present new computational methods that make large-scale nonlinear network inference tractable. First, we exploit the topology of networks describing potential interactions among chemical species to design improved 'between-model' proposals for reversible-jump Markov chain Monte Carlo. Second, we introduce a sensitivity-based determination of move types which, when combined with network-aware proposals, yields significant additional gains in sampling performance. These algorithms are demonstrated on inference problems drawn from systems biology, with nonlinear differential equation models of species interactions.

Efficient design and verification of diagnostics for impurity transport experiments

Recent attempts to measure impurity transport in Alcator C-Mod using an x-ray imaging crystal spectrometer and laser blow-off impurity injector have failed to yield unique reconstructions of the transport coefficient profiles. This paper presents a fast, linearized model which was constructed to estimate diagnostic requirements for impurity transport experiments. The analysis shows that the spectroscopic diagnostics on Alcator C-Mod should be capable of inferring simple profiles of impurity diffusion D_Z and convection V_Z accurate to better than ±10% uncertainty, suggesting that the failure to infer unique D_Z and V_Z from experimental data is attributable to an inadequate analysis procedure rather than the result of insufficient diagnostics. Furthermore, the analysis reveals that even a modest spatial resolution can overcome a low time resolution. This approach can be adapted to design and verify diagnostics for transport experiments on any magnetic confinement device.

A Bayesian approach for estimating bioterror attacks from patient data

Terrorist attacks using an aerosolized pathogen have gained credibility as a national security concern after the anthrax attacks of 2001. Inferring some important details of the attack quickly, for example, the number of people infected, the time of infection, and a representative dose received can be crucial to planning a medical response. We use a Bayesian approach, based on a short time series of diagnosed patients, to estimate a joint probability density for these parameters. We first test the formulation with idealized cases and then apply it to realistic scenarios, including the Sverdlovsk anthrax outbreak of 1979. We also use simulated outbreaks to explore the impact of model error, as when the model used for generating simulated epidemic curves does not match the model subsequently used to characterize the attack. We find that in all cases except for the smallest attacks (fewer than 100 infected people), 3-5 days of data are sufficient to characterize the outbreak to a specificity that is useful for directing an emergency response.