Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Neural Networks with Cheap Differential Operators
Ricky T. Q. Chen, David K. Duvenaud
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use exact trace computation with HollowNet instead of stochastic trace estimation | continuous normalizing flows · MNIST | -ELBO: 82.82 ± 0.01 -> 82.37 ± 0.04 | Improved |
| use exact trace computation with HollowNet instead of stochastic trace estimation | continuous normalizing flows · Omniglot | -ELBO: 98.33 ± 0.09 -> 97.42 ± 0.05 | Improved |
| use exact trace computation with HollowNet rather than stochastic trace estimation | continuous normalizing flows · MNIST | NLL: 80.22 ± 0.08 vs 80.22 ± 0.03 | No clear effect |
| use exact trace computation with HollowNet rather than stochastic trace estimation | continuous normalizing flows · Omniglot | NLL: 93.90 ± 0.14 vs 93.77 ± 0.03 | No clear effect |
| use exact trace rather than stochastic trace estimation | continuous normalizing flows · MINIBOONE | training NLL | Improved |
| use Fokker–Planck matching instead of pseudo-maximum likelihood | SDE models · synthetic pendulum with sparse observations | mean absolute error of drift and diffusion | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FFJORD — FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models (ICLR 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Operator-Learning-Inspired Modeling of Neural Ordinary Differential Equations (AAAI 2024 · similarity 0.90)
- Derivative-enhanced Deep Operator Network (NeurIPS 2024 · similarity 0.87)
- Sensitivity-Constrained Fourier Neural Operators for Forward and Inverse Problems in Parametric Differential Equations (ICLR 2025 · similarity 0.87)
- Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators (NeurIPS 2024 · similarity 0.87)
- Semi-Implicit Neural Ordinary Differential Equations (AAAI 2025 · similarity 0.87)
- Component Fourier Neural Operator for Singularly Perturbed Differential Equations (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
