Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Stephen Roberts

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


Jul 16, 2021
Shaan Desai, Marios Mattheakis, David Sondak, Pavlos Protopapas, Stephen Roberts

* [under review] 

  Access Paper or Ask Questions

Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL


Jun 30, 2021
Jack Parker-Holder, Vu Nguyen, Shaan Desai, Stephen Roberts


  Access Paper or Ask Questions

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


Jun 18, 2021
Kieran Wood, Stephen Roberts, Stefan Zohren

* minor corrections, strategy comparison for 2015-2020 made more robust by repeated trials 

  Access Paper or Ask Questions

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


Jun 17, 2021
Lewis Smith, Joost van Amersfoort, Haiwen Huang, Stephen Roberts, Yarin Gal

* Main paper 10 pages including references, appendix 10 pages. 7 figures and 6 tables including appendix 

  Access Paper or Ask Questions

Enhancing Cross-Sectional Currency Strategies by Ranking Refinement with Transformer-based Architectures


May 20, 2021
Daniel Poh, Bryan Lim, Stefan Zohren, Stephen Roberts

* 7 pages, 3 figures 

  Access Paper or Ask Questions

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


Apr 12, 2021
Philip J. Ball, Cong Lu, Jack Parker-Holder, Stephen Roberts

* To be presented as a Spotlight at the "Self-Supervision for Reinforcement Learning Workshop" @ ICLR 2021 

  Access Paper or Ask Questions

Adversarial Robustness Guarantees for Gaussian Processes


Apr 07, 2021
Andrea Patane, Arno Blaas, Luca Laurenti, Luca Cardelli, Stephen Roberts, Marta Kwiatkowska

* Submitted for publication 

  Access Paper or Ask Questions

Building Cross-Sectional Systematic Strategies By Learning to Rank


Dec 13, 2020
Daniel Poh, Bryan Lim, Stefan Zohren, Stephen Roberts

* 12 pages, 3 figures 

  Access Paper or Ask Questions

Explaining the Adaptive Generalisation Gap


Nov 15, 2020
Diego Granziol, Samuel Albanie, Xingchen Wan, Stephen Roberts


  Access Paper or Ask Questions

SafePILCO: a software tool for safe and data-efficient policy synthesis


Aug 07, 2020
Kyriakos Polymenakos, Nikitas Rontsis, Alessandro Abate, Stephen Roberts

* Shorter Version published as a software tool demonstration at QEST 2020 

  Access Paper or Ask Questions

Explicit Regularisation in Gaussian Noise Injections


Jul 14, 2020
Alexander Camuto, Matthew Willetts, Umut Şimşekli, Stephen Roberts, Chris Holmes

* 10 Pages 

  Access Paper or Ask Questions

Towards a Theoretical Understanding of the Robustness of Variational Autoencoders


Jul 14, 2020
Alexander Camuto, Matthew Willetts, Stephen Roberts, Chris Holmes, Tom Rainforth

* 10 Pages 

  Access Paper or Ask Questions

Relaxed-Responsibility Hierarchical Discrete VAEs


Jul 14, 2020
Matthew Willetts, Xenia Miscouridou, Stephen Roberts, Chris Holmes

* 10 Pages 

  Access Paper or Ask Questions

On Optimism in Model-Based Reinforcement Learning


Jun 21, 2020
Aldo Pacchiano, Philip Ball, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts


  Access Paper or Ask Questions

Deep Learning for Portfolio Optimisation


May 27, 2020
Zihao Zhang, Stefan Zohren, Stephen Roberts

* 12 pages, 6 figures 

  Access Paper or Ask Questions

VIGN: Variational Integrator Graph Networks


Apr 28, 2020
Shaan Desai, Stephen Roberts


  Access Paper or Ask Questions

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


Apr 08, 2020
Jaleh Zand, Stephen Roberts


  Access Paper or Ask Questions

Iterate Averaging Helps: An Alternative Perspective in Deep Learning


Mar 02, 2020
Diego Granziol, Xingchen Wan, Stephen Roberts

* 9 pages, 8 figures, 21 pages including references and appendix 

  Access Paper or Ask Questions

Learning Bijective Feature Maps for Linear ICA


Feb 19, 2020
Alexander Camuto, Matthew Willetts, Brooks Paige, Chris Holmes, Stephen Roberts

* 8 pages 

  Access Paper or Ask Questions

HumBug Zooniverse: a crowd-sourced acoustic mosquito dataset


Feb 14, 2020
Ivan Kiskin, Adam D. Cobb, Lawrence Wang, Stephen Roberts

* Awarded Best Paper at the 2019 NeurIPS ML4D workshop. Accepted at ICASSP 2020 

  Access Paper or Ask Questions

Ready Policy One: World Building Through Active Learning


Feb 07, 2020
Philip Ball, Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts


  Access Paper or Ask Questions

One-Shot Bayes Opt with Probabilistic Population Based Training


Feb 06, 2020
Jack Parker-Holder, Vu Nguyen, Stephen Roberts


  Access Paper or Ask Questions

Effective Diversity in Population-Based Reinforcement Learning


Feb 03, 2020
Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts


  Access Paper or Ask Questions

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


Jan 23, 2020
Bryan Lim, Stefan Zohren, Stephen Roberts


  Access Paper or Ask Questions

Safety Guarantees for Planning Based on Iterative Gaussian Processes


Jan 17, 2020
Kyriakos Polymenakos, Luca Laurenti, Andrea Patane, Jan-Peter Calliess, Luca Cardelli, Marta Kwiatkowska, Alessandro Abate, Stephen Roberts

* Preprint, shorter version presented in NeurIPS-2019 Workshop on Safety and Robustness in Decision Making 

  Access Paper or Ask Questions

MLRG Deep Curvature


Dec 20, 2019
Diego Granziol, Xingchen Wan, Timur Garipov, Dmitry Vetrov, Stephen Roberts

* 11 pages, 11 figures 

  Access Paper or Ask Questions

A Maximum Entropy approach to Massive Graph Spectra


Dec 19, 2019
Diego Granziol, Robin Ru, Stefan Zohren, Xiaowen Dong, Michael Osborne, Stephen Roberts

* 12 pages. 9 Figures 

  Access Paper or Ask Questions