no code implementations • 1 Apr 2024 • Maud Lemercier, Terry Lyons
As bounded variation paths (and more generally geometric $p$-rough paths) can be approximated by piecewise smooth rough paths, one can replace the PDE with rapidly varying coefficients in the original Goursat problem by an explicit system of coupled equations with piecewise constant coefficients derived from the first few iterated integrals of the original input paths.
no code implementations • 22 Feb 2024 • Paola Arrubarrena, Maud Lemercier, Bojan Nikolic, Terry Lyons, Thomas Cass
We demonstrate how SigNova improves the detection of various types of RFI (e. g., broadband and narrowband) in time-frequency visibility data.
1 code implementation • NeurIPS 2023 • Zacharia Issa, Blanka Horvath, Maud Lemercier, Cristopher Salvi
Neural SDEs are continuous-time generative models for sequential data.
1 code implementation • 30 Mar 2023 • Nicola Muca Cirone, Maud Lemercier, Cristopher Salvi
Motivated by the paradigm of reservoir computing, we consider randomly initialized controlled ResNets defined as Euler-discretizations of neural controlled differential equations (Neural CDEs), a unified architecture which enconpasses both RNNs and ResNets.
1 code implementation • 19 Oct 2021 • Cristopher Salvi, Maud Lemercier, Andris Gerasimovics
On the other hand, it extends Neural Operators -- generalizations of neural networks to model mappings between spaces of functions -- in that it can parameterize solution operators of SPDEs depending simultaneously on the initial condition and a realization of the driving noise.
1 code implementation • NeurIPS 2021 • Cristopher Salvi, Maud Lemercier, Chong Liu, Blanka Hovarth, Theodoros Damoulas, Terry Lyons
Stochastic processes are random variables with values in some space of paths.
no code implementations • 10 May 2021 • Maud Lemercier, Cristopher Salvi, Thomas Cass, Edwin V. Bonilla, Theodoros Damoulas, Terry Lyons
Making predictions and quantifying their uncertainty when the input data is sequential is a fundamental learning challenge, recently attracting increasing attention.
no code implementations • 10 Jun 2020 • Maud Lemercier, Cristopher Salvi, Theodoros Damoulas, Edwin V. Bonilla, Terry Lyons
In this paper, we develop a rigorous mathematical framework for distribution regression where inputs are complex data streams.