Research map / Probabilistic and scientific modeling / Variational and generative sampling
Accelerating Continuous Normalizing Flow with Trajectory Polynomial Regularization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add trajectory polynomial regularization to FFJORD | FFJORD · Density estimation: POWER, GAS, HEPMASS, MINIBOONE, BSDS300, MNIST, CIFAR10 | average NFE: The reduction of NFE ranges from 42.3% to 71.3%. | Helped |
| Add trajectory polynomial regularization to FFJORD | FFJORD · VAE: MNIST, Omniglot, Frey Faces, Caltech Silhouettes | average NFE: ranging from 19.3% to 32.1% | Helped |
| Add trajectory polynomial regularization to FFJORD | FFJORD · Density estimation: POWER, GAS, HEPMASS, MINIBOONE, BSDS300, MNIST, CIFAR10 | testing loss | Mixed |
| Add trajectory polynomial regularization to FFJORD | FFJORD · VAE: MNIST, Omniglot, Frey Faces, Caltech Silhouettes | testing negative ELBO | No clear effect |
Closest papers by meaning
- An Error Analysis of Flow Matching for Deep Generative Modeling (ICML 2025 · similarity 0.87)
- Robustly Train Normalizing Flows via KL Divergence Regularization (AAAI 2024 · similarity 0.86)
- Reflected Flow Matching (ICML 2024 · similarity 0.85)
- Asymptotically exact variational flows via involutive MCMC kernels (NeurIPS 2025 · similarity 0.85)
- Fast and unified path gradient estimators for normalizing flows (ICLR 2024 · similarity 0.85)
- Importance Corrected Neural JKO Sampling (ICML 2025 · similarity 0.84)
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.