Tim Sullivan

Junior Professor in Applied Mathematics:
Risk and Uncertainty Quantification

Strong convergence rates of probabilistic integrators for ordinary differential equations

Preprint: Strong convergence rates of probabilistic integrators for ODEs

Han Cheng Lie, Andrew Stuart and I have just uploaded a preprint of our latest paper, “Strong convergence rates of probabilistic integrators for ordinary differential equations” to the arXiv. This paper is a successor to the convergence results presented by Conrad et al. (2016). We consider a generic probabilistic solver for an ODE, using a fixed time step of length \(\tau > 0\), where the mean of the solver has global error of order \(\tau^{q}\) and the variance of the truncation error model has order \(\tau^{1 + 2 p}\). Whereas Conrad et al. showed, for a Lipschitz driving vector field, that the mean-square error between the numerical solution \(U_{k}\) and the true solution \(u_{k}\) is bounded uniformly in time as

\( \displaystyle \max_{0 \leq k \leq T / \tau} \mathbb{E} [ \| U_{k} - u_{k} \|^{2} ] \leq C \tau^{2 \min \{ p, q \}} \)

(i.e. has the same order of convergence as the underlying deterministic method), we are able to relax the regularity assumptions on the vector field / flow an obtain a stronger mode of convergence (mean-square in the uniform norm) with the same convergence rate:

\( \displaystyle \mathbb{E} \left[ \max_{0 \leq k \leq T / \tau} \| U_{k} - u_{k} \|^{2} \right] \leq C \tau^{2 \min \{ p, q \}} \)

Abstract. Probabilistic integration of a continuous dynamical system is a way of systematically introducing model error, at scales no larger than errors inroduced by standard numerical discretisation, in order to enable thorough exploration of possible responses of the system to inputs. It is thus a potentially useful approach in a number of applications such as forward uncertainty quantification, inverse problems, and data assimilation. We extend the convergence analysis of probabilistic integrators for deterministic ordinary differential equations, as proposed by Conrad et al. (Stat. Comput., 2016), to establish mean-square convergence in the uniform norm on discrete- or continuous-time solutions under relaxed regularity assumptions on the driving vector fields and their induced flows. Specifically, we show that randomised high-order integrators for globally Lipschitz flows and randomised Euler integrators for dissipative vector fields with polynomially-bounded local Lipschitz constants all have the same mean-square convergence rate as their deterministic counterparts, provided that the variance of the integration noise is not of higher order than the corresponding deterministic integrator.

Published on Monday 13 March 2017 at 13:00 UTC #publication #preprint #prob-num

Bayesian probabilistic numerical methods

Preprint: Bayesian probabilistic numerical methods

Jon Cockayne, Chris Oates, Mark Girolami and I have just uploaded a preprint of our latest paper, “Bayesian probabilistic numerical methods” to the arXiv. Following on from our earlier work “Probabilistic meshless methods for partial differential equations and Bayesian inverse problems”, our aim is to provide some rigorous theoretical underpinnings for the emerging field of probabilistic numerics, and in particular to define what it means for such a method to be “Bayesian”, by connecting with the established theories of Bayesian inversion and disintegration of measures.

Abstract. The emergent field of probabilistic numerics has thus far lacked rigorous statistical principals. This paper establishes Bayesian probabilistic numerical methods as those which can be cast as solutions to certain Bayesian inverse problems, albeit problems that are non-standard. This allows us to establish general conditions under which Bayesian probabilistic numerical methods are well-defined, encompassing both non-linear and non-Gaussian models. For general computation, a numerical approximation scheme is developed and its asymptotic convergence is established. The theoretical development is then extended to pipelines of computation, wherein probabilistic numerical methods are composed to solve more challenging numerical tasks. The contribution highlights an important research frontier at the interface of numerical analysis and uncertainty quantification, with some illustrative applications presented.

Published on Tuesday 14 February 2017 at 12:00 UTC #publication #preprint #prob-num

Probabilistic numerical methods for PDE-constrained Bayesian inverse problems

Preprint: Probabilistic numerical methods for PDE-constrained Bayesian inverse problems

Jon Cockayne, Chris Oates, Mark Girolami and I have just uploaded a preprint of our latest paper, “Probabilistic numerical methods for PDE-constrained Bayesian inverse problems” to the arXiv. This paper is intended to complement our earlier work “Probabilistic meshless methods for partial differential equations and Bayesian inverse problems” and to give a more concise presentation of the main ideas, aimed at a general audience.

Published on Wednesday 18 January 2017 at 12:00 UTC #publication #preprint #prob-num

Jon Cockayne

UQ Talks: Jon Cockayne

Next week Jon Cockayne (University of Warwick) will give a talk on “Probabilistic Numerics for Partial Differential Equations”.

Time and Place. Friday 14 October 2016, 12:00–13:00, ZIB Seminar Room 2006, Zuse Institute Berlin, Takustraße 7, 14195 Berlin

Abstract. Probabilistic numerics is an emerging field which constructs probability measures to capture uncertainty arising from the discretisation which is often necessary to solve complex problems numerically. We explore probabilistic numerical methods for Partial differential equations (PDEs). We phrase solution of PDEs as a statistical inference problem, and construct probability measures which quantify the epistemic uncertainty in the solution resulting from the discretisation [1].

We analyse these probability measures in the context of Bayesian inverse problems, parameter inference problems whose dynamics are often constrained by a system of PDEs. Sampling from parameter posteriors in such problems often involves replacing an exact likelihood with an approximate one, in which a numerical approximation is substituted for the true solution of the PDE. Such approximations have been shown to produce biased and overconfident posteriors when error in the forward solver is not tightly controlled. We show how the uncertainty from a probabilistic forward solver can be propagated into the parameter posteriors, thus permitting the use of coarser discretisations while still producing valid statistical inferences.

[1] Jon Cockayne, Chris Oates, Tim Sullivan, and Mark Girolami. “Probabilistic Meshless Methods for Partial Differential Equations and Bayesian Inverse Problems.” arXiv preprint, 2016. arXiv:1605.07811

Published on Monday 3 October 2016 at 10:00 UTC #event #uq-talk #prob-num

Probabilistic Numerics at MCQMC

There will be a workshop on Probabilistic Numerics at this year's MCQMC conference at Stanford University. The workshop will be held on Thursday, 18 August 2016, 15:50–17:50, at the Li Ka Shing Center on the Stanford University campus. Speakers include:

  • Mark Girolami (University of Warwick & Alan Turing Institute) — Probabilistic Numerical Computation: A New Concept?
  • François-Xavier Briol (University of Warwick & University of Oxford) — Probabilistic Integration: A Role for Statisticians in Numerical Analysis?
  • Chris Oates (University of Technology Sydney) — Probabilistic Integration for Intractable Distributions
  • Jon Cockayne (University of Warwick) — Probabilistic meshless methods for partial differential equations and Bayesian inverse problems

Update, 19 August 2016. The slides from the talks can be found here, on Chris Oates' website.

Published on Sunday 31 July 2016 at 14:00 UTC #prob-num #event

← Newer | 1 | 2 | Older →