Research map / Probabilistic and scientific modeling / Variational and generative sampling
Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows
Cheng Zhang
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 |
|---|---|---|---|
| replace the diagonal Lognormal branch-length approximation with permutation equivariant RealNVP flows | VBPI (PSP) · DS1-DS8 | lower bound (K=10): DS1: -7108.73 -> -7108.58; DS8: -8651.88 -> -8651.41 | Improved |
| use permutation equivariant planar flows instead of the diagonal Lognormal approximation (ablation) | VBPI (PSP) · DS1-DS8 | lower bound (K=10): DS1: -7108.73 -> -7108.70; DS8: -8651.88 -> -8651.80 | Improved |
| increase planar flow depth from 16 to 32 layers (ablation) | VBPI-NF Planar · DS1-DS8 | lower bound (K=10): DS1: -7108.70 -> -7108.64; DS8: -8651.80 -> -8651.72 | Improved |
| use RealNVP flows rather than planar flows (ablation) | VBPI-NF · DS1-DS8 | lower bound (K=10): DS1: Planar(32) -7108.64; RealNVP(5) -7108.63; DS8: Planar(32) -8651.72; RealNVP(5) -8651.62 | Mixed |
| increase RealNVP depth from 5 to 10 layers (ablation) | VBPI-NF RealNVP · DS1-DS8 | lower bound (K=10): DS1: -7108.63 -> -7108.58; DS8: -8651.62 -> -8651.41 | Improved |
| use structured permutation equivariant flows with local topological information | VBPI-NF · DS1 95% credible set | amortization gap: All: 0.84 -> 0.72 | Improved |
| increase flow expressiveness using RealNVP(10) rather than PSP (ablation) | VBPI-NF · DS1 95% credible set | approximation gap: All: 1.21 -> 0.40 | Improved |
Closest papers by meaning
- Variational Phylogenetic Inference with Products over Bipartitions (ICML 2025 · similarity 0.89)
- PhyloGFN: Phylogenetic inference with generative flow networks (ICLR 2024 · similarity 0.88)
- PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation (NeurIPS 2024 · similarity 0.88)
- Likelihood-free inference of phylogenetic tree posterior distributions (NeurIPS 2026 · similarity 0.88)
- Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes (NeurIPS 2026 · similarity 0.87)
- PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders (ICLR 2025 · similarity 0.85)
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.
