REVIEW 6 cited by
Neural Controlled Differential Equations for Online Prediction Tasks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Neural controlled differential equations (Neural CDEs) are a continuous-time extension of recurrent neural networks (RNNs), achieving state-of-the-art (SOTA) performance at modelling functions of irregular time series. In order to interpret discrete data in continuous time, current implementations rely on non-causal interpolations of the data. This is fine when the whole time series is observed in advance, but means that Neural CDEs are not suitable for use in \textit{online prediction tasks}, where predictions need to be made in real-time: a major use case for recurrent networks. Here, we show how this limitation may be rectified. First, we identify several theoretical conditions that interpolation schemes for Neural CDEs should satisfy, such as boundedness and uniqueness. Second, we use these to motivate the introduction of new schemes that address these conditions, offering in particular measurability (for online prediction), and smoothness (for speed). Third, we empirically benchmark our online Neural CDE model on three continuous monitoring tasks from the MIMIC-IV medical database: we demonstrate improved performance on all tasks against ODE benchmarks, and on two of the three tasks against SOTA non-ODE benchmarks.
Forward citations
Cited by 6 Pith papers
-
CausticFlow: An Efficient Machine Learning Framework Combining Neural Differential Equations and Normalizing Flows for Binary Microlensing Parameter Inference
CausticFlow combines neural CDEs and normalizing flows to propose binary microlensing posteriors in under a second, recovering ~80% of simulated events and 7 of 10 real events after local polishing.
-
Time Resolution Independent Operator Learning
A DeepONet with a neural controlled differential equation branch and a trunk that takes space and time as inputs predicts transient mechanical fields from load histories at arbitrary spatiotemporal query points.
-
Early Detection of Hardware Trojans Using Neural Controlled Differential Equations and Analysis of Power Traces
An NCDE trained only on Trojan-free power traces plus an LDA threshold on prediction MSE separates clean, dormant-Trojan, and active-Trojan chips above a ~3% power-deviation sensitivity floor.
-
TrajSurv: Learning Continuous Latent Trajectories from Electronic Health Records for Trustworthy Survival Prediction
TrajSurv learns continuous latent patient trajectories from irregular EHR data using an NCDE, aligns them with SOFA severity scores via time-aware contrastive learning, and uses vector-field and trajectory-clustering ...
-
Data-driven modeling of a settling sphere in a quiescent medium
Neural ODE and neural SDE models trained on experimental particle tracks reproduce long-time statistics of a chaotic settling sphere, with deterministic models generalizing better to new initial conditions.
-
HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs
Modeling the full token-by-token trajectory of LLM hidden states with neural ODEs, CDEs, and SDEs improves hallucination detection by over 14% AUC on a constructed true/false benchmark, though gains shrink on QA datasets.
Discussion (0). Continue with ORCID to comment.