Full-day mini-course on Path Signatures
SURE-AI invites to a full-day mini-course on path signatures, a mathematical framework for representing sequential data, and its connections to modern machine learning.
- Starts:09:00, 16 March 2026
- Ends:16:00, 16 March 2026
- Location:BI - campus Oslo, room: A2-Blue 1
Path signatures provide a principled way to turn a time series or trajectory into a structured collection of features built from iterated integrals. Intuitively, these features capture not only increments but also ordered interactions between channels across time (such as area-type effects and higher-order dependencies). This makes signatures particularly well-suited to sequential learning: they give a fixed-dimensional representation (after truncation) that is robust to irregular sampling, supports efficient computation via concatenation identities, and can serve as an expressive feature map for regression and classification—often enabling strong performance even with relatively simple downstream models.
If you plan to attend, please feel free to drop by for the full day, or join for individual blocks depending on your interests. We hope this will provide a shared mathematical starting point for further discussions on sequential learning across the center.
Registration and the complete programme can be found on the official event page.
Programme
- Time
- Title
-
From paths to features: An introduction to the signature transform
Fabian Harang, Professor, Department of Economics - BI Norwegian Business School
-
From iterated sums to path signatures: An algebraic perspective
Kurusch Ebrahimi-Fard, Professor, Department of Mathematical Sciences - NTNU
-
Lunch
-
(Cont) From iterated sums to path signatures: An algebraic perspective
Kurusch Ebrahimi-Fard, Professor, Department of Mathematical Sciences - NTNU
-
Path development networks on finite-dimensional lie groups for sequential learning
Hao Ni, Professor of Mathematics, University College London (UCL)