Search Results for author: Stephen Roberts

Found 81 papers, 20 papers with code

Transfer Ranking in Finance: Applications to Cross-Sectional Momentum with Data Scarcity

no code implementations21 Aug 2022 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.

The ACM Multimedia 2022 Computational Paralinguistics Challenge: Vocalisations, Stuttering, Activity, & Mosquitoes

no code implementations13 May 2022 Björn W. Schuller, Anton Batliner, Shahin Amiriparian, Christian Bergler, Maurice Gerczuk, Natalie Holz, Pauline Larrouy-Maestri, Sebastian P. Bayerl, Korbinian Riedhammer, Adria Mallol-Ragolta, Maria Pateraki, Harry Coppock, Ivan Kiskin, Marianne Sinka, Stephen Roberts

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 Vocalisations and Stuttering Sub-Challenges, a classification on human non-verbal vocalisations and speech has to be made; the Activity Sub-Challenge aims at beyond-audio human activity recognition from smartwatch sensor data; and in the Mosquitoes Sub-Challenge, mosquitoes need to be detected.

Human Activity Recognition

Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture

2 code implementations16 Dec 2021 Kieran Wood, Sven Giegerich, Stephen Roberts, Stefan Zohren

We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies.

Time Series Variable Selection

A Bayesian take on option pricing with Gaussian processes

no code implementations7 Dec 2021 Martin Tegner, Stephen Roberts

Local volatility is a versatile option pricing model due to its state dependent diffusion coefficient.

Bayesian Inference Gaussian Processes

One-Shot Transfer Learning of Physics-Informed Neural Networks

1 code implementation21 Oct 2021 Shaan Desai, Marios Mattheakis, Hayden Joy, Pavlos Protopapas, Stephen Roberts

In this study, we present a general framework for transfer learning PINNs that results in one-shot inference for linear systems of both ordinary and partial differential equations.

Transfer Learning

Robust and Scalable SDE Learning: A Functional Perspective

no code implementations ICLR 2022 Scott Cameron, Tyron Cameron, Arnu Pretorius, Stephen Roberts

Stochastic differential equations provide a rich class of flexible generative models, capable of describing a wide range of spatio-temporal processes.

Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems

1 code implementation16 Jul 2021 Shaan Desai, Marios Mattheakis, David Sondak, Pavlos Protopapas, Stephen Roberts

In this study, we address the challenge of learning from such non-autonomous systems by embedding the port-Hamiltonian formalism into neural networks, a versatile framework that can capture energy dissipation and time-dependent control forces.

Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective

no code implementations4 Jun 2021 Lewis Smith, Joost van Amersfoort, Haiwen Huang, Stephen Roberts, Yarin Gal

ResNets constrained to be bi-Lipschitz, that is, approximately distance preserving, have been a crucial component of recently proposed techniques for deterministic uncertainty quantification in neural models.

Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection

2 code implementations28 May 2021 Kieran Wood, Stephen Roberts, Stefan Zohren

Back-testing our model over the period 1995-2020, the addition of the CPD module leads to an improvement in Sharpe ratio of one-third.

Change Point Detection Time Series

Enhancing Cross-Sectional Currency Strategies by Context-Aware Learning to Rank with Self-Attention

no code implementations20 May 2021 Daniel Poh, Bryan Lim, Stefan Zohren, Stephen Roberts

The performance of a cross-sectional currency strategy depends crucially on accurately ranking instruments prior to portfolio construction.

Information Retrieval Learning-To-Rank +2

Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment

no code implementations ICLR Workshop SSL-RL 2021 Philip J. Ball, Cong Lu, Jack Parker-Holder, Stephen Roberts

Reinforcement learning from large-scale offline datasets provides us with the ability to learn policies without potentially unsafe or impractical exploration.

Adversarial Robustness Guarantees for Gaussian Processes

1 code implementation7 Apr 2021 Andrea Patane, Arno Blaas, Luca Laurenti, Luca Cardelli, Stephen Roberts, Marta Kwiatkowska

Gaussian processes (GPs) enable principled computation of model uncertainty, making them attractive for safety-critical applications.

Adversarial Robustness Gaussian Processes

Building Cross-Sectional Systematic Strategies By Learning to Rank

no code implementations13 Dec 2020 Daniel Poh, Bryan Lim, Stefan Zohren, Stephen Roberts

The success of a cross-sectional systematic strategy depends critically on accurately ranking assets prior to portfolio construction.

Information Retrieval Learning-To-Rank +1

Investment sizing with deep learning prediction uncertainties for high-frequency Eurodollar futures trading

no code implementations31 Jul 2020 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 trades.

Towards a Theoretical Understanding of the Robustness of Variational Autoencoders

no code implementations14 Jul 2020 Alexander Camuto, Matthew Willetts, Stephen Roberts, Chris Holmes, Tom Rainforth

We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations.

Relaxed-Responsibility Hierarchical Discrete VAEs

no code implementations14 Jul 2020 Matthew Willetts, Xenia Miscouridou, Stephen Roberts, Chris Holmes

Successfully training Variational Autoencoders (VAEs) with a hierarchy of discrete latent variables remains an area of active research.

Towards Tractable Optimism in Model-Based Reinforcement Learning

no code implementations21 Jun 2020 Aldo Pacchiano, Philip J. Ball, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts

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).

Continuous Control Decision Making +3

Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training

no code implementations16 Jun 2020 Diego Granziol, Stefan Zohren, Stephen Roberts

Whilst the linear scaling for stochastic gradient descent has been derived under more restrictive conditions, which we generalise, the square root scaling rule for adaptive optimisers is, to our knowledge, completely novel.

Second-order methods

Deep Learning for Portfolio Optimization

2 code implementations27 May 2020 Zihao Zhang, Stefan Zohren, Stephen Roberts

We adopt deep learning models to directly optimise the portfolio Sharpe ratio.

Portfolio Optimization

Variational Integrator Graph Networks for Learning Energy Conserving Dynamical Systems

no code implementations28 Apr 2020 Shaan Desai, Marios Mattheakis, Stephen Roberts

Using this framework we introduce Variational Integrator Graph Networks - a novel method that unifies the strengths of existing approaches by combining an energy constraint, high-order symplectic variational integrators, and graph neural networks.

Inductive Bias

Mixture Density Conditional Generative Adversarial Network Models (MD-CGAN)

no code implementations8 Apr 2020 Jaleh Zand, Stephen Roberts

Generative Adversarial Networks (GANs) have gained significant attention in recent years, with impressive applications highlighted in computer vision in particular.

Time Series Forecasting

Iterative Averaging in the Quest for Best Test Error

no code implementations2 Mar 2020 Diego Granziol, Xingchen Wan, Samuel Albanie, Stephen Roberts

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 dimensional quadratic.

Image Classification

Learning Bijective Feature Maps for Linear ICA

no code implementations18 Feb 2020 Alexander Camuto, Matthew Willetts, Brooks Paige, Chris Holmes, Stephen Roberts

Separating high-dimensional data like images into independent latent factors, i. e independent component analysis (ICA), remains an open research problem.

Ready Policy One: World Building Through Active Learning

no code implementations ICML 2020 Philip Ball, Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts

Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks.

Active Learning Continuous Control +1

Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

1 code implementation NeurIPS 2020 Jack Parker-Holder, Vu Nguyen, Stephen Roberts

A recent solution to this problem is Population Based Training (PBT) which updates both weights and hyperparameters in a single training run of a population of agents.

Hyperparameter Optimization

Detecting Changes in Asset Co-Movement Using the Autoencoder Reconstruction Ratio

no code implementations23 Jan 2020 Bryan Lim, Stefan Zohren, Stephen Roberts

Detecting changes in asset co-movements is of much importance to financial practitioners, with numerous risk management benefits arising from the timely detection of breakdowns in historical correlations.

Denoising Dimensionality Reduction +1

HumBug Zooniverse: a crowd-sourced acoustic mosquito dataset

1 code implementation14 Jan 2020 Ivan Kiskin, Adam D. Cobb, Lawrence Wang, Stephen Roberts

Mosquitoes are the only known vector of malaria, which leads to hundreds of thousands of deaths each year.

Towards understanding the true loss surface of deep neural networks using random matrix theory and iterative spectral methods

no code implementations ICLR 2020 Diego Granziol, Timur Garipov, Dmitry Vetrov, Stefan Zohren, Stephen Roberts, Andrew Gordon Wilson

This approach is an order of magnitude faster than state-of-the-art methods for spectral visualization, and can be generically used to investigate the spectral properties of matrices in deep learning.

A Maximum Entropy approach to Massive Graph Spectra

no code implementations19 Dec 2019 Diego Granziol, Robin Ru, Stefan Zohren, Xiaowen Dong, Michael Osborne, Stephen Roberts

Graph spectral techniques for measuring graph similarity, or for learning the cluster number, require kernel smoothing.

Graph Similarity

Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning

no code implementations4 Dec 2019 Samuel Kessler, Vu Nguyen, Stefan Zohren, Stephen Roberts

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.

Continual Learning Variational Inference

Deep Reinforcement Learning for Trading

no code implementations22 Nov 2019 Zihao Zhang, Stefan Zohren, Stephen Roberts

We adopt Deep Reinforcement Learning algorithms to design trading strategies for continuous futures contracts.

reinforcement-learning Time Series

Balancing Reconstruction Quality and Regularisation in ELBO for VAEs

no code implementations9 Sep 2019 Shuyu Lin, Stephen Roberts, Niki Trigoni, Ronald Clark

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.

Improving VAEs' Robustness to Adversarial Attack

no code implementations ICLR 2021 Matthew Willetts, Alexander Camuto, Tom Rainforth, Stephen Roberts, Chris Holmes

We make significant advances in addressing this issue by introducing methods for producing adversarially robust VAEs.

Adversarial Attack

Adversarial Robustness Guarantees for Classification with Gaussian Processes

1 code implementation28 May 2019 Arno Blaas, Andrea Patane, Luca Laurenti, Luca Cardelli, Marta Kwiatkowska, Stephen Roberts

We apply our method to investigate the robustness of GPC models on a 2D synthetic dataset, the SPAM dataset and a subset of the MNIST dataset, providing comparisons of different GPC training techniques, and show how our method can be used for interpretability analysis.

Adversarial Robustness Classification +2

Population-based Global Optimisation Methods for Learning Long-term Dependencies with RNNs

no code implementations23 May 2019 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 optimisation methods.

reinforcement-learning Time Series

Enhancing Time Series Momentum Strategies Using Deep Neural Networks

1 code implementation9 Apr 2019 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.

Time Series

A Machine Learning approach to Risk Minimisation in Electricity Markets with Coregionalized Sparse Gaussian Processes

no code implementations22 Mar 2019 Daniel Poh, Stephen Roberts, Martin Tegnér

Secondly, in demonstrating that our model-based strategy outperforms the comparator, and can thus be employed for effective hedging in electricity markets.

BIG-bench Machine Learning Gaussian Processes +2

WiSE-ALE: Wide Sample Estimator for Approximate Latent Embedding

no code implementations16 Feb 2019 Shuyu Lin, Ronald Clark, Robert Birke, Niki Trigoni, Stephen Roberts

Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data.

Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction

1 code implementation23 Jan 2019 Bryan Lim, Stefan Zohren, Stephen Roberts

Testing this on three real-world time series datasets, we demonstrate that the decoupled representations learnt not only improve the accuracy of one-step-ahead forecasts while providing realistic uncertainty estimates, but also facilitate multistep prediction through the separation of encoder stages.

Time Series Prediction

Portfolio Optimization for Cointelated Pairs: SDEs vs. Machine Learning

no code implementations26 Dec 2018 Babak Mahdavi-Damghani, Konul Mustafayeva, Stephen Roberts, Cristin Buescu

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 problem of dynamic portfolio optimization in continuous-time, finite-horizon setting for a portfolio of two assets that are intertwined.

BIG-bench Machine Learning Portfolio Optimization

Practical Bayesian Learning of Neural Networks via Adaptive Optimisation Methods

1 code implementation8 Nov 2018 Samuel Kessler, Arnold Salas, Vincent W. C. Tan, Stefan Zohren, Stephen Roberts

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 optimisation algorithms such as AdaGrad and Adam.

Multi-Armed Bandits Thompson Sampling

Semi-unsupervised Learning of Human Activity using Deep Generative Models

1 code implementation29 Oct 2018 Matthew Willetts, Aiden Doherty, Stephen Roberts, Chris Holmes

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 others entirely unlabelled.

Classification General Classification +3

A General Framework for Fair Regression

no code implementations10 Oct 2018 Jack Fitzsimons, AbdulRahman Al Ali, Michael Osborne, Stephen Roberts

Fairness, through its many forms and definitions, has become an important issue facing the machine learning community.

Fairness Gaussian Processes +1

DeepLOB: Deep Convolutional Neural Networks for Limit Order Books

3 code implementations10 Aug 2018 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.

Computational Finance

Sequential sampling of Gaussian process latent variable models

no code implementations13 Jul 2018 Martin Tegner, Benjamin Bloem-Reddy, Stephen Roberts

We consider the problem of inferring a latent function in a probabilistic model of data.

Entropic Spectral Learning for Large-Scale Graphs

no code implementations18 Apr 2018 Diego Granziol, Binxin Ru, Stefan Zohren, Xiaowen Dong, Michael Osborne, Stephen Roberts

Graph spectra have been successfully used to classify network types, compute the similarity between graphs, and determine the number of communities in a network.

Community Detection

MOrdReD: Memory-based Ordinal Regression Deep Neural Networks for Time Series Forecasting

1 code implementation26 Mar 2018 Bernardo Pérez Orozco, Gabriele Abbati, Stephen Roberts

In this work, we directly tackle this task with a novel, fully end-to-end deep learning method for time series forecasting.

Astronomy regression +1

Gradient descent in Gaussian random fields as a toy model for high-dimensional optimisation in deep learning

no code implementations24 Mar 2018 Mariano Chouza, Stephen Roberts, Stefan Zohren

Besides complementing our analytical findings with numerical results from simulated Gaussian random fields, we also compare it to loss functions obtained from optimisation problems on synthetic and real data sets by proposing a "black box" random field toy-model for a deep neural network loss function.

Safe Policy Search with Gaussian Process Models

1 code implementation15 Dec 2017 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.

Mosquito detection with low-cost smartphones: data acquisition for malaria research

no code implementations16 Nov 2017 Yunpeng Li, Davide Zilli, Henry Chan, Ivan Kiskin, Marianne Sinka, Stephen Roberts, Kathy Willis

Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year.

Entropic Determinants

no code implementations8 Sep 2017 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 which calculating the log determinant is a canonical example.

Mosquito Detection with Neural Networks: The Buzz of Deep Learning

no code implementations15 May 2017 Ivan Kiskin, Bernardo Pérez Orozco, Theo Windebank, Davide Zilli, Marianne Sinka, Kathy Willis, Stephen Roberts

The huge advances enjoyed by many application domains in recent years have been fuelled by the use of deep learning architectures trained on large data sets.

Event Detection Informativeness +2

Entropic Trace Estimates for Log Determinants

1 code implementation24 Apr 2017 Jack Fitzsimons, Diego Granziol, Kurt Cutajar, Michael Osborne, Maurizio Filippone, Stephen Roberts

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 processes, generalised Markov random fields, graph models and many others.

Gaussian Processes Point Processes

Bayesian Inference of Log Determinants

no code implementations5 Apr 2017 Jack Fitzsimons, Kurt Cutajar, Michael Osborne, Stephen Roberts, Maurizio Filippone

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 to the training of Gaussian processes.

Bayesian Inference Gaussian Processes +1

Extracting Predictive Information from Heterogeneous Data Streams using Gaussian Processes

no code implementations20 Mar 2016 Sid Ghoshal, Stephen Roberts

Financial markets are notoriously complex environments, presenting vast amounts of noisy, yet potentially informative data.

Gaussian Processes Sentiment Analysis +1

Blitzkriging: Kronecker-structured Stochastic Gaussian Processes

no code implementations27 Oct 2015 Thomas Nickson, Tom Gunter, Chris Lloyd, Michael A. Osborne, Stephen Roberts

We present Blitzkriging, a new approach to fast inference for Gaussian processes, applicable to regression, optimisation and classification.

Gaussian Processes General Classification +2

String and Membrane Gaussian Processes

no code implementations24 Jul 2015 Yves-Laurent Kom Samo, Stephen Roberts

In particular, we prove that some string GPs are Gaussian processes, which provides a complementary global perspective on our framework.

Bayesian Inference Gaussian Processes

String Gaussian Process Kernels

no code implementations7 Jun 2015 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 (string GPs).

Gaussian Processes

Generalized Spectral Kernels

no code implementations7 Jun 2015 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 arbitrary precision).

Detecting bird sound in unknown acoustic background using crowdsourced training data

no code implementations24 May 2015 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 crowdsourcing using recording and species recognition on mobile devices.

Scalable Nonparametric Bayesian Inference on Point Processes with Gaussian Processes

no code implementations24 Oct 2014 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 to introducing latent thinning points.

Bayesian Inference Gaussian Processes +1

Communication Communities in MOOCs

no code implementations18 Mar 2014 Nabeel Gillani, Rebecca Eynon, Michael Osborne, Isis Hjorth, Stephen Roberts

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 or communicate.

online learning

Conservative collision prediction and avoidance for stochastic trajectories in continuous time and space

no code implementations17 Feb 2014 Jan-Peter Calliess, Michael Osborne, Stephen Roberts

Existing work in multi-agent collision prediction and avoidance typically assumes discrete-time trajectories with Gaussian uncertainty or that are completely deterministic.

Efficient State-Space Inference of Periodic Latent Force Models

no code implementations23 Oct 2013 Steven Reece, Stephen Roberts, Siddhartha Ghosh, Alex Rogers, Nicholas Jennings

We apply our approach to model the thermal dynamics of domestic buildings and show that it is effective at predicting day-ahead temperatures within the homes.

Cannot find the paper you are looking for? You can Submit a new open access paper.