Vietnam Spring School
Machine learning and rough path theory for sequential data analysis
The purpose of this research school is to showcase recent developments in Rough Path Theory (RPT) in machine learning (ML) for understanding complex multimodal data streams. This 5-day spring school is composed of 9 mini courses delivered by leading experts in this field, to cover topics from methodological innovation to real-world applications. Two invited keynote talks, along with a panel discussion, will further broaden the scope of the mini courses and stimulate the discussion on general mathematical approaches in ML and data science.
Scientific committee
Juergen Jost, Max Planck Institute for Mathematics in the Sciences, Germany
Terry Lyons, University of Oxford, United Kingdom
Organising committee
Duc Luu, MIS-Germany & Institute of Mathematics, VAST, Vietnam
Hao Ni, University College London, United Kingdom
Viet Hung Pham, Institute of Mathematics, VAST, Vietnam
Speakers
| Terry Lyons | The connection between rough paths and data science |
| Juergen Jost | Mathematical approaches for the analysis of data |
| Harald Oberhauser | Describing laws of stochastic processes with expected signature moments and cumulants |
| Thomas Cass | Topologies and functions on unparameterised path space |
| Maud Lemercier | Signature Kernel Methods |
| Cris Salvi | Infinite width-depth regimes of Recurrent ResNets |
| Emilio Rossi Ferrucci | Foundation of rough path theory |
| Yue Wu | An introduction to the log-ODE method |
| Hao Ni | Generative models for time series generation: a rough path approach |
| Weixin Yang | Developing the path signature methodology and its applications to some real-world machine learning challenges |
| Duc Luu | Tracking attractors via discrete rough paths |
| Nam Vo | Machine Learning Methods for the Understanding of the Human Genome |
