arXiv subjects

Matthew Sutton

Publications and source records attributed to Matthew Sutton.

13 recordsLinked to original sources

arXiv2026

Cytoarchitecture in Words: Weakly Supervised Vision-Language Modeling for Human Brain Microscopy

Vision foundation models increasingly support interactive scientific workflows, but natural-language interaction requires coupling visual representations to language. Curated image-text pairs for this coupling are scarce in many biomedical domains. This is the case for cell-body-stained histological sections of the human brain, where microscopic image patches encode cytoarchitecture: cellular density, morphology, laminar structure, and areal organization. We propose retrieve-and-enrich supervision, a weakly supervised scheme for training image-conditioned language models without curated image-text pairs. The method retrieves label-level text from the literature via a shared anatomical label, then enriches it with image-specific properties such as cortical layer thickness and cell density. Labels provide training targets only, not model inputs. We use this scheme to couple CytoNet, a cytoarchitectonic vision foundation model, to an open-weight large language model via a lightweight Flamingo-style adapter. Across 57 brain areas, the resulting model produces plausible cytoarchitectonic descriptions, supports open-set use by rejecting out-of-scope areas, and predicts the correct area for in-scope patches with 90.6% accuracy. Removing explicit area names from generated text still leaves descriptions sufficient for a language model to recover the area in an 8-way test with 68.6% accuracy. A second instruction-tuned model trained with image-specific targets recovers cortical layer thickness and cell-densities from individual patches, allowing the model to read out information beyond canonical area descriptions. Our results show that retrieve-and-enrich supervision offers a practical route to vision-language training in specialized imaging domains where labels and expert text exist but image-level captions do not.

cs.CV↗

arXiv2025

Towards practical PDMP sampling: Metropolis adjustments, locally adaptive step-sizes, and NUTS-based time lengths

Piecewise-Deterministic Markov Processes (PDMPs) hold significant promise for sampling from complex probability distributions. However, their practical implementation is hindered by the need to compute model-specific bounds. Conversely, while Hamiltonian Monte Carlo (HMC) offers a generally efficient approach to sampling, its inability to adaptively tune step sizes impedes its performance when sampling complex distributions like funnels. To address these limitations, we introduce three innovative concepts: (a) a Metropolis-adjusted approximation for PDMP simulation that eliminates the need for explicit bounds without compromising the invariant measure, (b) an adaptive step size mechanism compatible with the Metropolis correction, and (c) a No U-Turn Sampler (NUTS)-inspired scheme for dynamically selecting path lengths in PDMPs. These three ideas can be seamlessly integrated into a single, `doubly-adaptive' PDMP sampler with favourable robustness and efficiency properties.

stat.CO↗

arXiv2024

The Polynomial Stein Discrepancy for Assessing Moment Convergence

We propose a novel method for measuring the discrepancy between a set of samples and a desired posterior distribution for Bayesian inference. Classical methods for assessing sample quality like the effective sample size are not appropriate for scalable Bayesian sampling algorithms, such as stochastic gradient Langevin dynamics, that are asymptotically biased. Instead, the gold standard is to use the kernel Stein Discrepancy (KSD), which is itself not scalable given its quadratic cost in the number of samples. The KSD and its faster extensions also typically suffer from the curse of dimensionality and can require extensive tuning. To address these limitations, we develop the polynomial Stein discrepancy (PSD) and an associated goodness-of-fit test. While the new test is not fully convergence-determining, we prove that it detects differences in the first r moments for Gaussian targets. We empirically show that the test has higher power than its competitors in several examples, and at a lower computational cost. Finally, we demonstrate that the PSD can assist practitioners to select hyper-parameters of Bayesian sampling algorithms more efficiently than competitors.

stat.ML↗

arXiv2024

Scalable Vertical Federated Learning via Data Augmentation and Amortized Inference

Vertical federated learning (VFL) has emerged as a paradigm for collaborative model estimation across multiple clients, each holding a distinct set of covariates. This paper introduces the first comprehensive framework for fitting Bayesian models in the VFL setting. We propose a novel approach that leverages data augmentation techniques to transform VFL problems into a form compatible with existing Bayesian federated learning algorithms. We present an innovative model formulation for specific VFL scenarios where the joint likelihood factorizes into a product of client-specific likelihoods. To mitigate the dimensionality challenge posed by data augmentation, which scales with the number of observations and clients, we develop a factorized amortized variational approximation that achieves scalability independent of the number of observations. We showcase the efficacy of our framework through extensive numerical experiments on logistic regression, multilevel regression, and a novel hierarchical Bayesian split neural net model. Our work paves the way for privacy-preserving, decentralized Bayesian inference in vertically partitioned data scenarios, opening up new avenues for research and applications in various domains.

stat.CO↗

arXiv2024

Control Variates for MCMC

This chapter describes several control variate methods for improving estimates of expectations from MCMC.

stat.ME↗

arXiv2023

Debiasing Piecewise Deterministic Markov Process samplers using couplings

Monte Carlo methods -- such as Markov chain Monte Carlo (MCMC) and piecewise deterministic Markov process (PDMP) samplers -- provide asymptotically exact estimators of expectations under a target distribution. There is growing interest in alternatives to this asymptotic regime, in particular in constructing estimators that are exact in the limit of an infinite amount of computing processors, rather than in the limit of an infinite number of Markov iterations. In particular, Jacob et al. (2020) introduced coupled MCMC estimators to remove the non-asymptotic bias, resulting in MCMC estimators that can be embarrassingly parallelised. In this work, we extend the estimators of Jacob et al. (2020) to the continuous-time context and derive couplings for the bouncy, the boomerang and the coordinate samplers. Some preliminary empirical results are included that demonstrate the reasonable scaling of our method with the dimension of the target.

stat.CO↗

arXiv2022

Transport Reversible Jump Proposals

Reversible jump Markov chain Monte Carlo (RJMCMC) proposals that achieve reasonable acceptance rates and mixing are notoriously difficult to design in most applications. Inspired by recent advances in deep neural network-based normalizing flows and density estimation, we demonstrate an approach to enhance the efficiency of RJMCMC sampling by performing transdimensional jumps involving reference distributions. In contrast to other RJMCMC proposals, the proposed method is the first to apply a non-linear transport-based approach to construct efficient proposals between models with complicated dependency structures. It is shown that, in the setting where exact transports are used, our RJMCMC proposals have the desirable property that the acceptance probability depends only on the model probabilities. Numerical experiments demonstrate the efficacy of the approach.

stat.CO↗

arXiv2022

Continuously-Tempered PDMP Samplers

New sampling algorithms based on simulating continuous-time stochastic processes called piece-wise deterministic Markov processes (PDMPs) have shown considerable promise. However, these methods can struggle to sample from multi-modal or heavy-tailed distributions. We show how tempering ideas can improve the mixing of PDMPs in such cases. We introduce an extended distribution defined over the state of the posterior distribution and an inverse temperature, which interpolates between a tractable distribution when the inverse temperature is 0 and the posterior when the inverse temperature is 1. The marginal distribution of the inverse temperature is a mixture of a continuous distribution on [0,1) and a point mass at 1: which means that we obtain samples when the inverse temperature is 1, and these are draws from the posterior, but sampling algorithms will also explore distributions at lower temperatures which will improve mixing. We show how PDMPs, and particularly the Zig-Zag sampler, can be implemented to sample from such an extended distribution. The resulting algorithm is easy to implement and we show empirically that it can outperform existing PDMP-based samplers on challenging multimodal posteriors.

stat.ME↗

arXiv2021

Concave-Convex PDMP-based sampling

Recently non-reversible samplers based on simulating piecewise deterministic Markov processes (PDMPs) have shown potential for efficient sampling in Bayesian inference problems. However, there remains a lack of guidance on how to best implement these algorithms. If implemented poorly, the computational costs of simulating event times can out-weigh the statistical efficiency of the non-reversible dynamics. Drawing on the adaptive rejection literature, we propose the concave-convex adaptive thinning approach for simulating a piecewise deterministic Markov process (CC-PDMP). This approach provides a general guide for constructing bounds that may be used to facilitate PDMP-based sampling. A key advantage of this method is its additive structure - adding concave-convex decompositions yields a concave-convex decomposition. This facilitates swapping priors, simple implementation and computationally efficient thinning. In particular, our approach is well suited to local PDMP simulation where known conditional independence of the target can be exploited for potentially huge computational gains. We provide an R package for implementing the CC-PDMP approach and illustrate how our method outperforms existing approaches to simulating events in the PDMP literature.

stat.ME↗

arXiv2021

Bayesian Detectability of Induced Polarisation in Airborne Electromagnetic Data using Reversible Jump Sequential Monte Carlo

Detection of induced polarisation (IP) effects in airborne electromagnetic (AEM) measurements does not yet have an established methodology. This contribution develops a Bayesian approach to the IP-detectability problem using decoupled transdimensional layered models, and applies an approach novel to geophysics whereby transdimensional proposals are used within the embarrassingly parallelisable and robust static Sequential Monte Carlo (SMC) class of algorithms for the simultaneous inference of parameters and models. Henceforth referring to this algorithm as Reversible Jump Sequential Monte Carlo (RJSMC), the statistical methodological contributions to the algorithm account for adaptivity considerations for multiple models and proposal types, especially surrounding particle impoverishment in unlikely models. Methodological contributions to solid Earth geophysics include the decoupled model approach and proposal of a statistic that use posterior model odds for IP detectability. A case study is included investigating detectability of IP effects in AEM data at a broad scale.

stat.AP↗

arXiv2020

Reversible Jump PDMP Samplers for Variable Selection

A new class of Markov chain Monte Carlo (MCMC) algorithms, based on simulating piecewise deterministic Markov processes (PDMPs), have recently shown great promise: they are non-reversible, can mix better than standard MCMC algorithms, and can use subsampling ideas to speed up computation in big data scenarios. However, current PDMP samplers can only sample from posterior densities that are differentiable almost everywhere, which precludes their use for model choice. Motivated by variable selection problems, we show how to develop reversible jump PDMP samplers that can jointly explore the discrete space of models and the continuous space of parameters. Our framework is general: it takes any existing PDMP sampler, and adds two types of trans-dimensional moves that allow for the addition or removal of a variable from the model. We show how the rates of these trans-dimensional moves can be calculated so that the sampler has the correct invariant distribution. Simulations show that the new samplers can mix better than standard MCMC algorithms. Our empirical results show they are also more efficient than gradient-based samplers that avoid model choice through use of continuous spike-and-slab priors which replace a point mass at zero for each parameter with a density concentrated around zero.

stat.CO↗

arXiv2018

Sampling molecular conformations and dynamics in a multi-user virtual reality framework

We describe a framework for interactive molecular dynamics in a multiuser virtual reality environment, combining rigorous cloud-mounted physical atomistic simulation with commodity virtual reality hardware, which we have made accessible to readers (see isci.itch.io/nsb-imd). It allows users to visualize and sample, with atomic-level precision, the structures and dynamics of complex molecular structures 'on the fly', and to interact with other users in the same virtual environment. A series of controlled studies, wherein participants were tasked with a range of molecular manipulation goals (threading methane through a nanotube, changing helical screw-sense, and tying a protein knot), quantitatively demonstrate that users within the interactive VR environment can complete sophisticated molecular modelling tasks more quickly than they can using conventional interfaces, especially for molecular pathways and structural transitions whose conformational choreographies are intrinsically 3d. This framework should accelerate progress in nanoscale molecular engineering areas such as drug development, synthetic biology, and catalyst design. More broadly, our findings highlight VR's potential in scientific domains where 3d dynamics matter, spanning research and education.

physics.chem-ph↗

arXiv2017

A Unified Parallel Algorithm for Regularized Group PLS Scalable to Big Data

Partial Least Squares (PLS) methods have been heavily exploited to analyse the association between two blocs of data. These powerful approaches can be applied to data sets where the number of variables is greater than the number of observations and in presence of high collinearity between variables. Different sparse versions of PLS have been developed to integrate multiple data sets while simultaneously selecting the contributing variables. Sparse modelling is a key factor in obtaining better estimators and identifying associations between multiple data sets. The cornerstone of the sparsity version of PLS methods is the link between the SVD of a matrix (constructed from deflated versions of the original matrices of data) and least squares minimisation in linear regression. We present here an accurate description of the most popular PLS methods, alongside their mathematical proofs. A unified algorithm is proposed to perform all four types of PLS including their regularised versions. Various approaches to decrease the computation time are offered, and we show how the whole procedure can be scalable to big data sets.

stat.ML↗