
PortHamiltonian Neural Networks for Learning Explicit TimeDependent Dynamical Systems
Accurately learning the temporal behavior of dynamical systems requires ...
read it

Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL
Despite a series of recent successes in reinforcement learning (RL), man...
read it

Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
ResNets constrained to be biLipschitz, that is, approximately distance ...
read it

Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection
Momentum strategies are an important part of alternative investments and...
read it

Enhancing CrossSectional Currency Strategies by Ranking Refinement with Transformerbased Architectures
The performance of a crosssectional currency strategy depends crucially...
read it

Augmented World Models Facilitate ZeroShot Dynamics Generalization From a Single Offline Environment
Reinforcement learning from largescale offline datasets provides us wit...
read it

Adversarial Robustness Guarantees for Gaussian Processes
Gaussian processes (GPs) enable principled computation of model uncertai...
read it

Building CrossSectional Systematic Strategies By Learning to Rank
The success of a crosssectional systematic strategy depends critically ...
read it

Explaining the Adaptive Generalisation Gap
We conjecture that the reason for the difference in generalisation betwe...
read it

SafePILCO: a software tool for safe and dataefficient policy synthesis
SafePILCO is a software tool for safe and dataefficient policy search w...
read it

Explicit Regularisation in Gaussian Noise Injections
We study the regularisation induced in neural networks by Gaussian noise...
read it

Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
We make inroads into understanding the robustness of Variational Autoenc...
read it

RelaxedResponsibility Hierarchical Discrete VAEs
Successfully training Variational Autoencoders (VAEs) with a hierarchy o...
read it

On Optimism in ModelBased Reinforcement Learning
The principle of optimism in the face of uncertainty is prevalent throug...
read it

Deep Learning for Portfolio Optimisation
We adopt deep learning models to directly optimise the portfolio Sharpe ...
read it

VIGN: Variational Integrator Graph Networks
Rich, physicallyinformed inductive biases play an imperative role in ac...
read it

Mixture Density Conditional Generative Adversarial Network Models (MDCGAN)
Generative Adversarial Networks (GANs) have gained significant attention...
read it

Iterate Averaging Helps: An Alternative Perspective in Deep Learning
Iterate averaging has a rich history in optimisation, but has only very ...
read it

Learning Bijective Feature Maps for Linear ICA
Separating highdimensional data like images into independent latent fac...
read it

Ready Policy One: World Building Through Active Learning
ModelBased Reinforcement Learning (MBRL) offers a promising direction f...
read it

OneShot Bayes Opt with Probabilistic Population Based Training
Selecting optimal hyperparameters is a key challenge in machine learning...
read it

Effective Diversity in PopulationBased Reinforcement Learning
Maintaining a population of solutions has been shown to increase explora...
read it

HumBug Zooniverse: a crowdsourced acoustic mosquito dataset
Mosquitoes are the only known vector of malaria, which leads to hundreds...
read it

MLRG Deep Curvature
We present MLRG Deep Curvature suite, a PyTorchbased, opensource packa...
read it

A Maximum Entropy approach to Massive Graph Spectra
Graph spectral techniques for measuring graph similarity, or for learnin...
read it

Indian Buffet Neural Networks for Continual Learning
We place an Indian Buffet Process (IBP) prior over the neural structure ...
read it

Safety Guarantees for Planning Based on Iterative Gaussian Processes
Gaussian Processes (GPs) are widely employed in control and learning bec...
read it

Deep Reinforcement Learning for Trading
We adopt Deep Reinforcement Learning algorithms to design trading strate...
read it

Stratified Space Learning: Reconstructing Embedded Graphs
Many datarich industries are interested in the efficient discovery and ...
read it

Regularising Deep Networks with DGMs
Here we develop a new method for regularising neural networks where we l...
read it

Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders
In clustering we normally output one cluster variable for each datapoint...
read it

Balancing Reconstruction Quality and Regularisation in ELBO for VAEs
A tradeoff exists between reconstruction quality and the prior regulari...
read it

MEMe: An Accurate Maximum Entropy Method for Efficient Approximations in LargeScale Machine Learning
Efficient approximation lies at the heart of largescale machine learnin...
read it

Disentangling Improves VAEs' Robustness to Adversarial Attacks
This paper is concerned with the robustness of VAEs to adversarial attac...
read it

Robustness Quantification for Classification with Gaussian Processes
We consider Bayesian classification with Gaussian processes (GPs) and de...
read it

Populationbased Global Optimisation Methods for Learning Longterm Dependencies with RNNs
Despite recent innovations in network architectures and loss functions, ...
read it

Enhancing Time Series Momentum Strategies Using Deep Neural Networks
While time series momentum is a wellstudied phenomenon in finance, comm...
read it

A Machine Learning approach to Risk Minimisation in Electricity Markets with Coregionalized Sparse Gaussian Processes
The nonstorability of electricity makes it unique among commodity asset...
read it

WiSEVAE: Wide Sample Estimator VAE
Variational Autoencoders (VAEs) have been very successful as methods fo...
read it

Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction
Despite the recent popularity of deep generative state space models, few...
read it

Portfolio Optimization for Cointelated Pairs: SDEs vs. Machine Learning
We investigate the problem of dynamic portfolio optimization in continuo...
read it

Bayesian deep neural networks for lowcost neurophysiological markers of Alzheimer's disease severity
As societies around the world are ageing, the number of Alzheimer's dise...
read it

Intersectionality: Multiple Group Fairness in Expectation Constraints
Group fairness is an important concern for machine learning researchers,...
read it

Practical Bayesian Learning of Neural Networks via Adaptive Subgradient Methods
We introduce a novel framework for the estimation of the posterior distr...
read it

Semiunsupervised Learning of Human Activity using Deep Generative Models
Here we demonstrate a new deep generative model for classification. We i...
read it

Equality Constrained Decision Trees: For the Algorithmic Enforcement of Group Fairness
Fairness, through its many forms and definitions, has become an importan...
read it

Sequential sampling of Gaussian process latent variable models
We consider the problem of inferring a latent function in a probabilisti...
read it

Sequential sampling of Gaussian latent variable models
We consider the problem of inferring a latent function in a probabilisti...
read it

Entropic Spectral Learning in Large Scale Networks
We present a novel algorithm for learning the spectral density of large ...
read it

MOrdReD: Memorybased Ordinal Regression Deep Neural Networks for Time Series Forecasting
Time series forecasting is ubiquitous in the modern world. Applications ...
read it
Stephen Roberts
is this you? claim profile
Professor of Machine Learning & Director, OxfordMan Institute of Quantitative Finance, University of Oxford