Algorithms & Computationally Intensive Inference seminars

Note:

Hybrid

Date

Speaker

Title

Note:

Hybrid

Note:

Hybrid

Note:

Hybrid

Abstract: Inference in stochastic reaction-network models—such as the SEIR epidemic model or the Lotka–Volterra predator–prey system—is crucial for understanding the dynamics of interacting systems in epidemiology, ecology, and systems biology. These models are typically represented as Markov jump processes (MJPs) with intractable likelihoods. As a result, particle Markov chain Monte Carlo (particle MCMC) methods, particularly the Particle Gibbs sampler, have become standard tools for Bayesian inference. However, PG suffers from severe particle degeneracy, especially in high-dimensional state spaces, leading to poor mixing and inefficiency.

In this talk, I focus on improving the efficiency of particle MCMC methods for inference in reaction networks by addressing the degeneracy problem. Building on recent work on the Exchangeable Particle Gibbs (xPG) sampler for continuous-state diffusions, this project develops a novel version of xPG tailored to discrete-state reaction networks, where randomness is driven by Poisson processes rather than Brownian motion. The proposed method retains the exchangeability framework of xPG while adapting it to the structural and computational challenges specific to reaction networks.

Note:

Hybrid

Note:

Hybrid

Abstract:

Note:

Hybrid

Abstract:

Note:

Hybrid

Abstract:

We propose a new simple and explicit numerical scheme for time-homogeneous stochastic differential equations. The scheme is based on sampling increments at each time step from a skew-symmetric probability distribution, with the level of skewness determined by the drift and volatility of the underlying process. We show that as the step-size decreases the scheme converges weakly to the diffusion of interest. We then consider the problem of simulating from the limiting distribution of an ergodic diffusion process using the numerical scheme with a fixed step-size. We establish conditions under which the numerical scheme converges to equilibrium at a geometric rate, and quantify the bias between the equilibrium distributions of the scheme and of the true diffusion process. Notably, our results do not require a global Lipschitz assumption on the drift, in contrast to those required for the Euler--Maruyama scheme for long-time simulation at fixed step-sizes. Our weak convergence result relies on an extension of the theory of Milstein & Tretyakov to stochastic differential equations with non-Lipschitz drift, which could also be of independent interest. We support our theoretical results with numerical simulations. This is a joint work with Samuel Livingstone, Nikolas Nüsken, Giorgos Vasdekis and Rui-Yang Zhang.

Note:

Hybrid

Abstract:

Co-evolutionary algorithms (CoEAs), which pair candidate designs with test cases, are frequently used in adversarial optimisation, particularly for binary test-based problems where designs and tests yield binary outcomes. The effectiveness of designs is determined by their performance against tests, and the value of tests is based on their ability to identify failing designs, often leading to more sophisticated tests and improved designs. However, CoEAs can exhibit complex, sometimes pathological behaviours like disengagement. Through runtime analysis, we aim to rigorously analyse whether CoEAs can efficiently solve test-based adversarial optimisation problems in an expected polynomial runtime. This paper carries out the first rigorous runtime analysis of (1, λ)-CoEA for binary test-based adversarial optimisation problems. In particular, we introduce a binary test-based benchmark problem called the Diagonal problem and initiate the first runtime analysis of competitive CoEA on this problem. The mathematical analysis shows that the (1, λ)-CoEA can efficiently find an ε approximation to the optimal solution of the Diagonal problem, i.e. in expected polynomial runtime assuming sufficiently low mutation rates and large offspring population size. On the other hand, the standard (1, λ)-EA fails to find an ε approximation to the optimal solution of the Diagonal problem in polynomial runtime. This illustrates the potential of coevolution for solving binary adversarial optimisation problems.

Arxiv link: https://arxiv.org/pdf/2407.17875.

Note:

Hybrid

Abstract:

Tempering is a popular tool in Bayesian computation, being used to transform a posterior distribution into a reference distribution that is more easily approximated. Several algorithms exist that start by approximating the reference distribution and proceed through a sequence of intermediate distributions until an approximation to the posterior is obtained. Our contribution reveals that high-quality approximation of terms up to the posterior is not essential, as knowledge of the intermediate distributions enables posterior quantities of interest to be extrapolated. Specifically, we establish conditions under which posterior expectations are determined by their associated tempered expectations on any non-empty interval. Harnessing this result, we propose novel methodology for approximating posterior expectations based on extrapolation and smoothing of tempered expectations, which we implement as a post-processing variance-reduction tool for sequential Monte Carlo.

Arxiv: https://arxiv.org/abs/2509.12173

Note:

Hybrid

Abstract:

Sampling from unnormalized densities, either for continuous or discrete variables, presents a fundamental challenge with wide-ranging applications, from posterior inference to molecular dynamics simulations and combinatorial optimisation. Continuous or discrete flow-based neural samplers offer a promising approach, learning a velocity field for continuous variable densities (or rate matrix for a continuous-time Markov chain (CTMC) built for discrete variable densities) that satisfies key principles of marginal density evolution (e.g., the continuity equation for continuous variable case and the Kolmogorov equation for discrete variable case) to generate samples. However, this learning procedure requires accurate estimation of intractable terms linked to the computationally challenging partition function, for which existing estimators often suffer from high variance or low accuracy. To overcome this, we introduce an improved estimator for these challenging quantities, employing an improved Sequential Monte Carlo method enhanced with control variates. We further introduce specific adjustments and advances for the trained sampler tailored for continuous variable or discrete variable case. In both scenarios, our proposed Neural Flow Samplers empirically outperforms existing flow-based neural samplers on both synthetic datasets and complex targets motivated by real-world applications.

Note:

Hybrid

Abstract:

Variational inference seeks the best approximation of a target distribution within a chosen family, where "best" means minimising Kullback-Leibler divergence. When the approximation family is exponential, the optimal approximation satisfies a fixed-point equation. We introduce LSVI (Least Squares Variational Inference), a gradient-free, Monte Carlo-based scheme for the fixed-point recursion, where each iteration boils down to performing ordinary least squares regression on tempered log-target evaluations under the variational approximation. We show that LSVI is equivalent to biased stochastic natural gradient descent and use this to derive convergence rates with respect to the numbers of samples and iterations. When the approximation family is Gaussian, LSVI involves inverting the Fisher information matrix, whose size grows quadratically with dimension d. We exploit the regression formulation to eliminate the need for this inversion, yielding O(d³) complexity in the full-covariance case and O(d) in the mean-field case. Finally, we numerically demonstrate LSVI’s performance on various tasks, including logistic regression, discrete variable selection, and Bayesian synthetic likelihood, showing competitive results with state-of-the-art methods, even when gradients are unavailable.

Arxiv: https://arxiv.org/abs/2502.18475