Research map / Probabilistic and scientific modeling / Variational and generative sampling
Embracing the chaos: analysis and diagnosis of numerical instability in variational flows
Zuheng Xu, Trevor Campbell
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 numerical (floating-point) flow orbits instead of exact orbits for trajectory averages | MixFlow · Banana, Cross, Lin. Reg., Log. Reg. | relative sample average error: around $1\%$ | No clear effect |
| Use numerical density evaluation instead of exact | MixFlow · four targets | relative log-density error: between $0.1\%$ and $1\%$ | No clear effect |
| Increase flow length N | MixFlow numerical ELBO · four targets | ELBO numerical error | No clear effect |
| Increase flow length N | MixFlow shadowing window · four targets | shadowing window size eps: smaller than $10^{-10}$ for length over $1000$ | Hurt |
| Increase flow length N | orbit computation error · synthetic examples | orbit error | Hurt |
Closest papers by meaning
- Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers (ICML 2025 · similarity 0.85)
- Asymptotically exact variational flows via involutive MCMC kernels (NeurIPS 2025 · similarity 0.85)
- SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories (NeurIPS 2025 · similarity 0.84)
- How to build a consistency model: Learning flow maps via self-distillation (NeurIPS 2025 · similarity 0.84)
- The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning (NeurIPS 2026 · similarity 0.84)
- The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling (NeurIPS 2026 · 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.
