Advances in Neural Controlled Differential Equations
Many real-world systems evolve continuously, yet most machine learning models interpret time series as discrete sequences. Continuous-time approaches instead treat time series as samples from an underlying input path, a formulation that naturally accommodates irregularly sampled or oversampled data. Among these, Neural Controlled Differential Equations (NCDEs) are a maximally expressive class of models that parametrise a vector field using a neural network and evolve their hidden state by solving a dynamical system driven by the input path. NCDEs typically use a non-linear vector field, so the
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 59%SciML/NeuralPDE.jl →
- PossiblePossibly related (embedding) · 51%Principled approaches for extending neural architectures to function spaces for operator learning →
- PossiblePossibly related (embedding) · 46%Hamiltonian Neural Networks from a Differential Geometry Perspective [D] →
- LinkedLinked via arxiv author · 85%Benjamin Walker →
“Advances in Neural Controlled Differential Equations”
- PossiblePossibly related (embedding) · 50%Enabling local neural operators to perform equation-free system-level analysis →