Random Controlled Differential Equations
Francesco Piatti, Thomas Cass, William F. Turner
TL;DR
The paper presents a training-efficient framework for time-series learning by combining large random continuous-time reservoirs with controlled differential equations. Two architectures, RF-CDE and R-RDE, lift input signals either via random Fourier features or log-signatures on rough paths, respectively, and train only a linear readout. In the infinite-width limit, RF-CDE converges to the RBF-lifted signature kernel and R-RDE to the rough signature kernel, providing Gaussian-process priors over path-functionals. Empirically, the methods achieve competitive or state-of-the-art performance on time-series benchmarks while offering scalable alternatives to explicit signature computations. The work unifies random feature reservoirs, continuous-time deep architectures, and path-signature theory with practical implementations (RandomSigJax) and robust experimental validation.
Abstract
We introduce a training-efficient framework for time-series learning that combines random features with controlled differential equations (CDEs). In this approach, large randomly parameterized CDEs act as continuous-time reservoirs, mapping input paths to rich representations. Only a linear readout layer is trained, resulting in fast, scalable models with strong inductive bias. Building on this foundation, we propose two variants: (i) Random Fourier CDEs (RF-CDEs): these lift the input signal using random Fourier features prior to the dynamics, providing a kernel-free approximation of RBF-enhanced sequence models; (ii) Random Rough DEs (R-RDEs): these operate directly on rough-path inputs via a log-ODE discretization, using log-signatures to capture higher-order temporal interactions while remaining stable and efficient. We prove that in the infinite-width limit, these model induces the RBF-lifted signature kernel and the rough signature kernel, respectively, offering a unified perspective on random-feature reservoirs, continuous-time deep architectures, and path-signature theory. We evaluate both models across a range of time-series benchmarks, demonstrating competitive or state-of-the-art performance. These methods provide a practical alternative to explicit signature computations, retaining their inductive bias while benefiting from the efficiency of random features.