Deep signature transforms
The signature is an infinite graded sequence of statistics known to characterise a stream of data up to a negligible equivalence class. It is a transform which has previously been treated as a fixed feature transformation, on top of which a model may be built. We propose a novel approach which combi...
Main Authors: | Bonnier, P, Kidger, P, Perez Arribas, I, Salvi, C, Lyons, T |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Curran Associates
2019
|
Similar Items
-
Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU
by: Kidger, P, et al.
Published: (2021) -
Universal approximation with deep narrow networks
by: Kidger, P, et al.
Published: (2020) -
A generalised signature method for multivariate time series feature extraction
by: Morrill, J, et al.
Published: (2020) -
Optimal execution with rough path signatures
by: Kalsi, J, et al.
Published: (2020) -
Neural rough differential equations for long time series
by: Morrill, J, et al.
Published: (2021)