AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows

Cheng Zhang

NeurIPS 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow-based density estimation · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace the diagonal Lognormal branch-length approximation with permutation equivariant RealNVP flowsVBPI (PSP) · DS1-DS8lower bound (K=10): DS1: -7108.73 -> -7108.58; DS8: -8651.88 -> -8651.41Improved
use permutation equivariant planar flows instead of the diagonal Lognormal approximation (ablation)VBPI (PSP) · DS1-DS8lower bound (K=10): DS1: -7108.73 -> -7108.70; DS8: -8651.88 -> -8651.80Improved
increase planar flow depth from 16 to 32 layers (ablation)VBPI-NF Planar · DS1-DS8lower bound (K=10): DS1: -7108.70 -> -7108.64; DS8: -8651.80 -> -8651.72Improved
use RealNVP flows rather than planar flows (ablation)VBPI-NF · DS1-DS8lower bound (K=10): DS1: Planar(32) -7108.64; RealNVP(5) -7108.63; DS8: Planar(32) -8651.72; RealNVP(5) -8651.62Mixed
increase RealNVP depth from 5 to 10 layers (ablation)VBPI-NF RealNVP · DS1-DS8lower bound (K=10): DS1: -7108.63 -> -7108.58; DS8: -8651.62 -> -8651.41Improved
use structured permutation equivariant flows with local topological informationVBPI-NF · DS1 95% credible setamortization gap: All: 0.84 -> 0.72Improved
increase flow expressiveness using RealNVP(10) rather than PSP (ablation)VBPI-NF · DS1 95% credible setapproximation gap: All: 1.21 -> 0.40Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy