Publications (113)
Robust Audio Tagging under Class-wise Supervision Unreliability
Yuanbo Hou, Zhaoyi Liu, Tong Ye +4
Weakly labeled datasets such as AudioSet have driven recent progress in audio tagging. However, annotation quality varies across sound classes. Labels may be incomplete, ambiguous,…
A large-scale and PCR-referenced vocal audio dataset for COVID-19
Jobie Budd, Kieran Baker, Emma Karoune +23
The UK COVID-19 Vocal Audio Dataset is designed for the training and evaluation of machine learning models that classify SARS-CoV-2 infection status or associated respiratory sympt…
Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture
Kieran Wood, Sven Giegerich, Stephen Roberts +1
We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike…
Learning Domain-Robust Bioacoustic Representations for Mosquito Species Classification with Contrastive Learning and Distribution Alignment
Yuanbo Hou, Zhaoyi Liu, Xin Shen +1
Mosquito Species Classification (MSC) is crucial for vector surveillance and disease control. The collection of mosquito bioacoustic data is often limited by mosquito activity seas…
Deep Learning for Options Trading: An End-To-End Approach
Wee Ling Tan, Stephen Roberts, Stefan Zohren
We introduce a novel approach to options trading strategies using a highly scalable and data-driven machine learning algorithm. In contrast to traditional approaches that often req…
Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction
Bryan Lim, Stefan Zohren, Stephen Roberts
Despite the recent popularity of deep generative state space models, few comparisons have been made between network architectures and the inference steps of the Bayesian filtering…
Investment sizing with deep learning prediction uncertainties for high-frequency Eurodollar futures trading
Trent Spears, Stefan Zohren, Stephen Roberts
In this work we show that prediction uncertainty estimates gleaned from deep learning models can be useful inputs for influencing the relative allocation of risk capital across tra…
Anomaly Detection and Removal Using Non-Stationary Gaussian Processes
Steven Reece, Roman Garnett, Michael Osborne +1
This paper proposes a novel Gaussian process approach to fault removal in time-series data. Fault removal does not delete the faulty signal data but, instead, massages the fault fr…
Extending Deep Learning Models for Limit Order Books to Quantile Regression
Zihao Zhang, Stefan Zohren, Stephen Roberts
We showcase how Quantile Regression (QR) can be applied to forecast financial returns using Limit Order Books (LOBs), the canonical data source of high-frequency financial time-ser…
Population-based Global Optimisation Methods for Learning Long-term Dependencies with RNNs
Bryan Lim, Stefan Zohren, Stephen Roberts
Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimi…
Enhancing Time Series Momentum Strategies Using Deep Neural Networks
Bryan Lim, Stefan Zohren, Stephen Roberts
While time series momentum is a well-studied phenomenon in finance, common strategies require the explicit definition of both a trend estimator and a position sizing rule. In this…
Adversarial Robustness Guarantees for Classification with Gaussian Processes
Arno Blaas, Andrea Patane, Luca Laurenti +3
We investigate adversarial robustness of Gaussian Process Classification (GPC) models. Given a compact subset of the input space enclosing a test point $x…
Scalable Nonparametric Bayesian Inference on Point Processes with Gaussian Processes
Yves-Laurent Kom Samo, Stephen Roberts
In this paper we propose the first non-parametric Bayesian model using Gaussian Processes to make inference on Poisson Point Processes without resorting to gridding the domain or t…
Efficient Bayesian Community Detection using Non-negative Matrix Factorisation
Ioannis Psorakis, Stephen Roberts, Ben Sheldon
Identifying overlapping communities in networks is a challenging task. In this work we present a novel approach to community detection that utilises the Bayesian non-negative matri…
Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
Alexander Camuto, Matthew Willetts, Stephen Roberts +2
We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations. While previous work has developed algorit…
A General Framework for Fair Regression
Jack Fitzsimons, AbdulRahman Al Ali, Michael Osborne +1
Fairness, through its many forms and definitions, has become an important issue facing the machine learning community. In this work, we consider how to incorporate group fairness c…
On statistical arbitrage under a conditional factor model of equity returns
Trent Spears, Stefan Zohren, Stephen Roberts
We consider a conditional factor model for a multivariate portfolio of United States equities in the context of analysing a statistical arbitrage trading strategy. A state space fr…
BioDCASE 2026 Challenge Baseline for Cross-Domain Mosquito Species Classification
Yuanbo Hou, Vanja Zdravkovic, Marianne Sinka +5
Mosquito-borne diseases affect more than one billion people each year and cause close to one million deaths. Traditional surveillance methods rely on traps and manual identificatio…
Explicit Regularisation in Gaussian Noise Injections
Alexander Camuto, Matthew Willetts, Umut ÅimÅekli +2
We study the regularisation induced in neural networks by Gaussian noise injections (GNIs). Though such injections have been extensively studied when applied to data, there have be…
Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning
Samuel Kessler, Vu Nguyen, Stefan Zohren +1
We place an Indian Buffet process (IBP) prior over the structure of a Bayesian Neural Network (BNN), thus allowing the complexity of the BNN to increase and decrease automatically.…
Sequential sampling of Gaussian process latent variable models
Martin Tegner, Benjamin Bloem-Reddy, Stephen Roberts
We consider the problem of inferring a latent function in a probabilistic model of data. When dependencies of the latent function are specified by a Gaussian process and the data l…
Bayesian deep neural networks for low-cost neurophysiological markers of Alzheimer's disease severity
Wolfgang Fruehwirt, Adam D. Cobb, Martin Mairhofer +11
As societies around the world are ageing, the number of Alzheimer's disease (AD) patients is rapidly increasing. To date, no low-cost, non-invasive biomarkers have been established…
Network Momentum across Asset Classes
Xingyue Pu, Stephen Roberts, Xiaowen Dong +1
We investigate the concept of network momentum, a novel trading signal derived from momentum spillover across assets. Initially observed within the confines of pairwise economic an…
G-TRACER: Expected Sharpness Optimization
John Williams, Stephen Roberts
We propose a new regularization scheme for the optimization of deep learning architectures, G-TRACER ("Geometric TRACE Ratio"), which promotes generalization by seeking flat minima…
Towards Tractable Optimism in Model-Based Reinforcement Learning
Aldo Pacchiano, Philip J. Ball, Jack Parker-Holder +2
The principle of optimism in the face of uncertainty is prevalent throughout sequential decision making problems such as multi-armed bandits and reinforcement learning (RL). To be…
BDLOB: Bayesian Deep Convolutional Neural Networks for Limit Order Books
Zihao Zhang, Stefan Zohren, Stephen Roberts
We showcase how dropout variational inference can be applied to a large-scale deep learning model that predicts price movements from limit order books (LOBs), the canonical data so…
Relaxed-Responsibility Hierarchical Discrete VAEs
Matthew Willetts, Xenia Miscouridou, Stephen Roberts +1
Successfully training Variational Autoencoders (VAEs) with a hierarchy of discrete latent variables remains an area of active research. Vector-Quantised VAEs are a powerful approac…
Mosquito detection with low-cost smartphones: data acquisition for malaria research
Yunpeng Li, Davide Zilli, Henry Chan +4
Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year. Not only is the prevention of mosquito bites of paramount impo…
Detecting bird sound in unknown acoustic background using crowdsourced training data
Timos Papadopoulos, Stephen Roberts, Kathy Willis
Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crow…
Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems
Shaan Desai, Marios Mattheakis, David Sondak +2
Accurately learning the temporal behavior of dynamical systems requires models with well-chosen learning biases. Recent innovations embed the Hamiltonian and Lagrangian formalisms…
Stratified Space Learning: Reconstructing Embedded Graphs
Yossi Bokor, Daniel Grixti-Cheng, Markus Hegland +2
Many data-rich industries are interested in the efficient discovery and modelling of structures underlying large data sets, as it allows for the fast triage and dimension reduction…
Blitzkriging: Kronecker-structured Stochastic Gaussian Processes
Thomas Nickson, Tom Gunter, Chris Lloyd +2
We present Blitzkriging, a new approach to fast inference for Gaussian processes, applicable to regression, optimisation and classification. State-of-the-art (stochastic) inference…
Robust and Scalable SDE Learning: A Functional Perspective
Scott Cameron, Tyron Cameron, Arnu Pretorius +1
Stochastic differential equations provide a rich class of flexible generative models, capable of describing a wide range of spatio-temporal processes. A host of recent work looks t…
Balancing Reconstruction Quality and Regularisation in ELBO for VAEs
Shuyu Lin, Stephen Roberts, Niki Trigoni +1
A trade-off exists between reconstruction quality and the prior regularisation in the Evidence Lower Bound (ELBO) loss that Variational Autoencoder (VAE) models use for learning. T…
Semi-unsupervised Learning of Human Activity using Deep Generative Models
Matthew Willetts, Aiden Doherty, Stephen Roberts +1
We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and…
DeepLOB: Deep Convolutional Neural Networks for Limit Order Books
Zihao Zhang, Stefan Zohren, Stephen Roberts
We develop a large-scale deep learning model to predict price movements from limit order book (LOB) data of cash equities. The architecture utilises convolutional filters to captur…
The ACM Multimedia 2022 Computational Paralinguistics Challenge: Vocalisations, Stuttering, Activity, & Mosquitoes
Björn W. Schuller, Anton Batliner, Shahin Amiriparian +12
The ACM Multimedia 2022 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the…
Safe Policy Search with Gaussian Process Models
Kyriakos Polymenakos, Alessandro Abate, Stephen Roberts
We propose a method to optimise the parameters of a policy which will be used to safely perform a given task in a data-efficient manner. We train a Gaussian process model to captur…
Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers
Harry Coppock, George Nicholson, Ivan Kiskin +22
Recent work has reported that AI classifiers trained on audio recordings can accurately predict severe acute respiratory syndrome coronavirus 2 (SARSCoV2) infection status. Here, w…
Transfer Ranking in Finance: Applications to Cross-Sectional Momentum with Data Scarcity
Daniel Poh, Stephen Roberts, Stefan Zohren
Cross-sectional strategies are a classical and popular trading style, with recent high performing variants incorporating sophisticated neural architectures. While these strategies…
Enhancing Cross-Sectional Currency Strategies by Context-Aware Learning to Rank with Self-Attention
Daniel Poh, Bryan Lim, Stefan Zohren +1
The performance of a cross-sectional currency strategy depends crucially on accurately ranking instruments prior to portfolio construction. While this ranking step is traditionally…
A Maximum Entropy approach to Massive Graph Spectra
Diego Granziol, Robin Ru, Stefan Zohren +3
Graph spectral techniques for measuring graph similarity, or for learning the cluster number, require kernel smoothing. The choice of kernel function and bandwidth are typically ch…
Statistics of Stellar Variability from Kepler - I: Revisiting Quarter 1 with an Astrophysically Robust Systematics Correction
Amy McQuillan, Suzanne Aigrain, Stephen Roberts
We investigate the variability properties of main sequence stars in the first month of Kepler data, using a new astrophysically robust systematics correction, and find that 60% of…
Model Merging by Output-Space Projection
Bethan Evans, Benjamin Etheridge, Stephen Roberts +1
Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups, TIES, and DARE - are compu…
Deep Inception Networks: A General End-to-End Framework for Multi-asset Quantitative Strategies
Tom Liu, Stephen Roberts, Stefan Zohren
We introduce Deep Inception Networks (DINs), a family of Deep Learning models that provide a general framework for end-to-end systematic trading strategies. DINs extract time serie…
Spectral Decompositions for Evolution Opertors of Mixing Dynamical Systems
Stephen Roberts, Boris Muzykantskii
Spectral decompositions for the evolution operator on an energy shell in phase space are constructed for the free motion on compact 2D surfaces of constant negative curvature. Appl…
One-Shot Transfer Learning of Physics-Informed Neural Networks
Shaan Desai, Marios Mattheakis, Hayden Joy +2
Solving differential equations efficiently and accurately sits at the heart of progress in many areas of scientific research, from classical dynamical systems to quantum mechanics.…
Generalized Spectral Kernels
Yves-Laurent Kom Samo, Stephen Roberts
In this paper we propose a family of tractable kernels that is dense in the family of bounded positive semi-definite functions (i.e. can approximate any bounded kernel with arbitra…
Effective Diversity in Population Based Reinforcement Learning
Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski +1
Exploration is a key problem in reinforcement learning, since agents can only learn from data they acquire in the environment. With that in mind, maintaining a population of agents…
First observations of the seiche that shook the world
Thomas Monahan, Tianning Tang, Stephen Roberts +1
On September 16th, 2023, an anomalous 10.88 mHz seismic signal was observed globally, persisting for 9 days. One month later an identical signal appeared, lasting for another week.…
Learning to Learn Financial Networks for Optimising Momentum Strategies
Xingyue Pu, Stefan Zohren, Stephen Roberts +1
Network momentum provides a novel type of risk premium, which exploits the interconnections among assets in a financial network to predict future returns. However, the current proc…
Deep Learning for Portfolio Optimization
Zihao Zhang, Stefan Zohren, Stephen Roberts
We adopt deep learning models to directly optimise the portfolio Sharpe ratio. The framework we present circumvents the requirements for forecasting expected returns and allows us…
Ready Policy One: World Building Through Active Learning
Philip Ball, Jack Parker-Holder, Aldo Pacchiano +2
Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks. However…
HumBug Zooniverse: a crowd-sourced acoustic mosquito dataset
Ivan Kiskin, Adam D. Cobb, Lawrence Wang +1
Mosquitoes are the only known vector of malaria, which leads to hundreds of thousands of deaths each year. Understanding the number and location of potential mosquito vectors is of…
Extracting Predictive Information from Heterogeneous Data Streams using Gaussian Processes
Sid Ghoshal, Stephen Roberts
Financial markets are notoriously complex environments, presenting vast amounts of noisy, yet potentially informative data. We consider the problem of forecasting financial time se…
Safety Guarantees for Planning Based on Iterative Gaussian Processes
Kyriakos Polymenakos, Luca Laurenti, Andrea Patane +5
Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step p…
Riemannian tangent space mapping and elastic net regularization for cost-effective EEG markers of brain atrophy in Alzheimer's disease
Wolfgang Fruehwirt, Matthias Gerstgrasser, Pengfei Zhang +11
The diagnosis of Alzheimer's disease (AD) in routine clinical practice is most commonly based on subjective clinical interpretations. Quantitative electroencephalography (QEEG) mea…
Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
Kunihiro Miyazaki, Takanobu Kawahara, Stephen Roberts +1
The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches deploy multi-agent systems mimi…
Learning Bijective Feature Maps for Linear ICA
Alexander Camuto, Matthew Willetts, Brooks Paige +2
Separating high-dimensional data like images into independent latent factors, i.e independent component analysis (ICA), remains an open research problem. As we show, existing proba…
Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL
Jack Parker-Holder, Vu Nguyen, Shaan Desai +1
Despite a series of recent successes in reinforcement learning (RL), many RL algorithms remain sensitive to hyperparameters. As such, there has recently been interest in the field…
Using Sparse Gaussian Processes for Predicting Robust Inertial Confinement Fusion Implosion Yields
Peter Hatfield, Steven Rose, Robbie Scott +3
Here we present the application of an advanced Sparse Gaussian Process based machine learning algorithm to the challenge of predicting the yields of inertial confinement fusion (IC…
Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection
Kieran Wood, Stephen Roberts, Stefan Zohren
Momentum strategies are an important part of alternative investments and are at the heart of commodity trading advisors (CTAs). These strategies have, however, been found to have d…
Improving VAEs' Robustness to Adversarial Attack
Matthew Willetts, Alexander Camuto, Tom Rainforth +2
Variational autoencoders (VAEs) have recently been shown to be vulnerable to adversarial attacks, wherein they are fooled into reconstructing a chosen target image. However, how to…
SafePILCO: a software tool for safe and data-efficient policy synthesis
Kyriakos Polymenakos, Nikitas Rontsis, Alessandro Abate +1
SafePILCO is a software tool for safe and data-efficient policy search with reinforcement learning. It extends the known PILCO algorithm, originally written in MATLAB, to support s…
Deep Reinforcement Learning for Trading
Zihao Zhang, Stefan Zohren, Stephen Roberts
We adopt Deep Reinforcement Learning algorithms to design trading strategies for continuous futures contracts. Both discrete and continuous action spaces are considered and volatil…
Variational Integrator Graph Networks for Learning Energy Conserving Dynamical Systems
Shaan Desai, Marios Mattheakis, Stephen Roberts
Recent advances show that neural networks embedded with physics-informed priors significantly outperform vanilla neural networks in learning and predicting the long term dynamics o…
An information and field theoretic approach to the grand canonical ensemble
Diego Granziol, Stephen Roberts
We present a novel derivation of the constraints required to obtain the underlying principles of statistical mechanics using a maximum entropy framework. We derive the mean value c…
Gradient descent in Gaussian random fields as a toy model for high-dimensional optimisation in deep learning
Mariano Chouza, Stephen Roberts, Stefan Zohren
In this paper we model the loss function of high-dimensional optimization problems by a Gaussian random field, or equivalently a Gaussian process. Our aim is to study gradient desc…
Portfolio Optimization for Cointelated Pairs: SDEs vs. Machine Learning
Babak Mahdavi-Damghani, Konul Mustafayeva, Stephen Roberts +1
With the recent rise of Machine Learning as a candidate to partially replace classic Financial Mathematics methodologies, we investigate the performances of both in solving the pro…
Bayesian Inference of Log Determinants
Jack Fitzsimons, Kurt Cutajar, Michael Osborne +2
The log-determinant of a kernel matrix appears in a variety of machine learning problems, ranging from determinantal point processes and generalized Markov random fields, through t…
A Machine Learning approach to Risk Minimisation in Electricity Markets with Coregionalized Sparse Gaussian Processes
Daniel Poh, Stephen Roberts, Martin Tegnér
The non-storability of electricity makes it unique among commodity assets, and it is an important driver of its price behaviour in secondary financial markets. The instantaneous an…
The instabilities of large learning rate training: a loss landscape view
Lawrence Wang, Stephen Roberts
Modern neural networks are undeniably successful. Numerous works study how the curvature of loss landscapes can affect the quality of solutions. In this work we study the loss land…
Novel Exploration Techniques (NETs) for Malaria Policy Interventions
Oliver Bent, Sekou L. Remy, Stephen Roberts +1
The task of decision-making under uncertainty is daunting, especially for problems which have significant complexity. Healthcare policy makers across the globe are facing problems…
Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders
Matthew Willetts, Stephen Roberts, Chris Holmes
In clustering we normally output one cluster variable for each datapoint. However it is not necessarily the case that there is only one way to partition a given dataset into cluste…
Communication Communities in MOOCs
Nabeel Gillani, Rebecca Eynon, Michael Osborne +2
Massive Open Online Courses (MOOCs) bring together thousands of people from different geographies and demographic backgrounds -- but to date, little is known about how they learn o…
Geo-ATBench: A Benchmark for Geospatial Audio Tagging with Geospatial Semantic Context
Yuanbo Hou, Yanru Wu, Qiaoqiao Ren +3
Environmental sound understanding in computational auditory scene analysis (CASA) is often formulated as an audio-only recognition problem. This formulation leaves a persistent dra…
Practical Bayesian Learning of Neural Networks via Adaptive Optimisation Methods
Samuel Kessler, Arnold Salas, Vincent W. C. Tan +2
We introduce a novel framework for the estimation of the posterior distribution over the weights of a neural network, based on a new probabilistic interpretation of adaptive optimi…
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits
Jack Parker-Holder, Vu Nguyen, Stephen Roberts
Many of the recent triumphs in machine learning are dependent on well-tuned hyperparameters. This is particularly prominent in reinforcement learning (RL) where a small change in t…
Entropic Spectral Learning for Large-Scale Graphs
Diego Granziol, Binxin Ru, Stefan Zohren +3
Graph spectra have been successfully used to classify network types, compute the similarity between graphs, and determine the number of communities in a network. For large graphs,…
Mixture Density Conditional Generative Adversarial Network Models (MD-CGAN)
Jaleh Zand, Stephen Roberts
Generative Adversarial Networks (GANs) have gained significant attention in recent years, with impressive applications highlighted in computer vision in particular. Compared to suc…
Lipschitz Interpolation: Non-parametric Convergence under Bounded Stochastic Noise
Julien Walden Huang, Stephen Roberts, Jan-Peter Calliess
This paper examines the asymptotic convergence properties of Lipschitz interpolation methods within the context of bounded stochastic noise. In the first part of the paper, we esta…
Entropic Determinants
Diego Granziol, Stephen Roberts
The ability of many powerful machine learning algorithms to deal with large data sets without compromise is often hampered by computationally expensive linear algebra tasks, of whi…
Entropic Trace Estimates for Log Determinants
Jack Fitzsimons, Diego Granziol, Kurt Cutajar +3
The scalable calculation of matrix determinants has been a bottleneck to the widespread application of many machine learning methods such as determinantal point processes, Gaussian…
On well-posed boundary conditions and energy stable finite volume method for the linear shallow water wave equation
Rudi Prihandoko, Kenneth Duru, Stephen Roberts +1
We derive and analyse well-posed boundary conditions for the linear shallow water wave equation. The analysis is based on the energy method and it identifies the number, location a…
Mosquito Detection with Neural Networks: The Buzz of Deep Learning
Ivan Kiskin, Bernardo Pérez Orozco, Theo Windebank +4
Many real-world time-series analysis problems are characterised by scarce data. Solutions typically rely on hand-crafted features extracted from the time or frequency domain allied…
Well-posed boundary conditions and energy stable discontinuous Galerkin spectral element method for the linearized Serre equations
Kenny Wiratama, Kenneth Duru, Stephen Roberts +1
We derive well-posed boundary conditions for the linearized Serre equations in one spatial dimension by utilizing the energy method. An energy stable and conservative discontinuous…
A Probabilistic Approach to Nonparametric Local Volatility
Martin Tegnér, Stephen Roberts
The local volatility model is a widely used for pricing and hedging financial derivatives. While its main appeal is its capability of reproducing any given surface of observed opti…
Intersectionality: Multiple Group Fairness in Expectation Constraints
Jack Fitzsimons, Michael Osborne, Stephen Roberts
Group fairness is an important concern for machine learning researchers, developers, and regulators. However, the strictness to which models must be constrained to be considered fa…
Adversarial Robustness Guarantees for Gaussian Processes
Andrea Patane, Arno Blaas, Luca Laurenti +3
Gaussian processes (GPs) enable principled computation of model uncertainty, making them attractive for safety-critical applications. Such scenarios demand that GP decisions are no…
Prediction-Oriented Subsampling from Data Streams
Benedetta Lavinia Mussati, Freddie Bickford Smith, Tom Rainforth +1
Data is often generated in streams, with new observations arriving over time. A key challenge for learning models from data streams is capturing relevant information while keeping…
Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Lewis Smith, Joost van Amersfoort, Haiwen Huang +2
ResNets constrained to be bi-Lipschitz, that is, approximately distance preserving, have been a crucial component of recently proposed techniques for deterministic uncertainty quan…
Strongly stable dual-pairing summation by parts finite difference schemes for the vector invariant nonlinear shallow water equations -- I: Numerical scheme and validation on the plane
Justin Kin Jun Hew, Kenneth Duru, Stephen Roberts +2
We present an energy/entropy stable and high order accurate finite difference (FD) method for solving the nonlinear (rotating) shallow water equations (SWEs) in vector invariant fo…
Dynamic Bayesian Combination of Multiple Imperfect Classifiers
Edwin Simpson, Stephen Roberts, Ioannis Psorakis +1
Classifier combination methods need to make best use of the outputs of multiple, imperfect classifiers to enable higher accuracy classifications. In many situations, such as when h…
Behaviour of the Serre Equations in the Presence of Steep Gradients Revisited
Jordan Pitt, Christopher Zoppou, Stephen Roberts
We use numerical methods to study the behaviour of the Serre equations in the presence of steep gradients because there are no known analytical solutions for these problems. In kee…
WiSE-ALE: Wide Sample Estimator for Approximate Latent Embedding
Shuyu Lin, Ronald Clark, Robert Birke +2
Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data. In this paper, we deri…
View fusion vis-Ã -vis a Bayesian interpretation of Black-Litterman for portfolio allocation
Trent Spears, Stefan Zohren, Stephen Roberts
The Black-Litterman model extends the framework of the Markowitz Modern Portfolio Theory to incorporate investor views. We consider a case where multiple view estimates, including…
VBALD - Variational Bayesian Approximation of Log Determinants
Diego Granziol, Edward Wagstaff, Bin Xin Ru +2
Evaluating the log determinant of a positive definite matrix is ubiquitous in machine learning. Applications thereof range from Gaussian processes, minimum-volume ellipsoids, metri…
String Gaussian Process Kernels
Yves-Laurent Kom Samo, Stephen Roberts
We introduce a new class of nonstationary kernels, which we derive as covariance functions of a novel family of stochastic processes we refer to as string Gaussian processes (strin…
Iterative Averaging in the Quest for Best Test Error
Diego Granziol, Xingchen Wan, Samuel Albanie +1
We analyse and explain the increased generalisation performance of iterate averaging using a Gaussian process perturbation model between the true and batch risk surface on the high…
Efficient State-Space Inference of Periodic Latent Force Models
Steven Reece, Stephen Roberts, Siddhartha Ghosh +2
Latent force models (LFM) are principled approaches to incorporating solutions to differential equations within non-parametric inference methods. Unfortunately, the development and…