In the era of ‘big data’, numerous data streams are being generated by individual activity, business processes and sensors. Data streams record complex sequences of events and are ubiquitous in everyday life; examples range from electronic financial trading records to human-computer interactions. Statistics and now machine learning have achieved considerable success in working with multimodal data streams. Rough Path Theory (RPT) provide a mathematical approach to the description of complex data streams; an approach that can be efficient, concise, robust to different sampling, assimilate new asynchronous features and is able to accommodate missing data. There are many contexts where incorporating these tools into the data analysis leads to improved efficiency (sometimes by orders of magnitude), quicker training and reduced power consumption.
RPT originated as a branch of stochastic analysis. It provides a rigorous framework for the analysis of controlled differential equations (CDEs) driven by highly oscillatory streams. Linear functionals on CDEs are a universally approximating family of functions on streams, that allows simple parameterization and is closed under concatenation. It is well adapted to modern frameworks of data science (optimization, back-propagation) in addition to the intrinsic ability to deal with evolving multi-modal data.
There are many exciting research questions and applications (e.g. algebraic methods providing a new structure theorem for information contained in streamed data, signature-based deep learning methods providing an efficient methodology for predicting cognitive development from longitudinal brain MRI data).
The aims of the workshop are:
•to present a range of research in RP theory for machine learning.
•to encourage dialogue between researchers from diverse disciplines and backgrounds, focusing on the methodology and applications of analysing complex data streams.
•to explore the potential for future collaboration.
This workshop will showcase mathematical methods and the applications in quantitative finance and human-computer interfaces.
13:00 - 13:10 Opening
13:10 - 13:50 Terry Lyons, University of Oxford - Title TBC
13:50 - 14:25 Xin Zhang, South China University of Technology - BrainPSNet: Multi-Stream Neural Network based Infant Cognitive Scores Prediction with Temporal Path Signature Features
14:25 - 15:00 Panel discussion
15:20 - 15:55 Joscha Diehl, University of Greifswald - Iterated sums and applications
15:55 - 16:30 Josef Teichmann, ETH Zürich - Randomized signature and reservoir computing
16:30 - 16:35 Closing remarks
- Terry Lyons, University of Oxford - Title TBC
- Xin Zhang, South China University of Technology - BrainPSNet: Multi-Stream Neural Network based Infant Cognitive Scores Prediction with Temporal Path Signature Features
- Joscha Diehl, University of Greifswald - Iterated sums and applications
- Josef Teichmann, ETH Zürich - Randomized signature and reservoir computing
Organised by the RSS Applied Probability Section jointly with the DataSig
Hao Ni, Department of Mathematics, UCL
Alex Watson, Statistical Science, UCL
RSS Fellows: FREE
RSS e-Students: FREE
All others: £10
Join the Society
as a Fellow.
(for free) as an e-Student.