pith. sign in

arxiv: 2011.03902 · v4 · pith:67N2VXKNnew · submitted 2020-11-08 · 💻 cs.LG · stat.ML

Learning Neural Event Functions for Ordinary Differential Equations

classification 💻 cs.LG stat.ML
keywords neuralchangeseventsystemsdiscretefunctionsknowledgemodeling
0
0 comments X
read the original abstract

The existing Neural ODE formulation relies on an explicit knowledge of the termination time. We extend Neural ODEs to implicitly defined termination criteria modeled by neural event functions, which can be chained together and differentiated through. Neural Event ODEs are capable of modeling discrete and instantaneous changes in a continuous-time system, without prior knowledge of when these changes should occur or how many such changes should exist. We test our approach in modeling hybrid discrete- and continuous- systems such as switching dynamical systems and collision in multi-body systems, and we propose simulation-based training of point processes with applications in discrete control.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Embedding Hybrid Systems into Continuous Latent Vector Fields

    cs.LG 2026-06 unverdicted novelty 7.0

    An n-dimensional hybrid system embeds into a continuous vector field in m > 2n dimensions, enabling latent Neural ODEs with consistency losses to recover hybrid flows from time series.

  2. Learning regime-dependent governing equations: A symbolic decision tree approach

    eess.SY 2026-05 unverdicted novelty 6.0

    A symbolic decision tree method is introduced to simultaneously learn interpretable regime partitions and local governing equations using basis function parametrization and mixed-integer optimization.

  3. RigidFormer: Learning Rigid Dynamics using Transformers

    cs.CV 2026-05 unverdicted novelty 6.0

    RigidFormer learns mesh-free rigid dynamics from point clouds using object-centric anchors, Anchor-Vertex Pooling, Anchor-based RoPE, and differentiable Kabsch alignment to enforce rigidity.

  4. Reconstructing and forecasting disease trajectories of patients with Alzheimer's disease using routine data in resource-constrained settings

    cs.AI 2026-06 unverdicted novelty 5.0

    GNOVA reconstructs and forecasts CDR-SB and MMSE scores with MAEs of 1.35 and 2.28 on 1727 ADNI patients over 10 years using only routine visit data, enabling interpolation, extrapolation, and uncertainty estimates.

  5. Model reduction of parametric ordinary differential equations via autoencoders: representation properties and convergence analysis

    math.NA 2025-09 unverdicted novelty 5.0

    Autoencoders enable nonlinear dimensionality reduction for parametric ODEs, with analysis of exact representation properties and convergence of the reduced model to the original.