Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies
Takahiro Mimori, Michiaki Hamada
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 wrapped normal 4-d full covariance instead of 2-d diagonal Q(z), LAX (ablation) | GeoPhy · DS1 | MLL: -7126.89 -> -7111.55 | Improved |
| use wrapped normal 4-d full covariance instead of 2-d diagonal Q(z), LAX (ablation) | GeoPhy · DS2 | MLL: -26444.84 -> -26379.48 | Improved |
| use wrapped normal 4-d full covariance instead of 2-d diagonal Q(z), LAX (ablation) | GeoPhy · DS7 | MLL: -37516.88 -> -37377.86 | Improved |
| swap LAX for LOO(3) control variate (WN(full,4)) (ablation) | GeoPhy · DS2 | MLL: -26379.48 -> -26368.44 | Improved |
| swap LAX for LOO(3) control variate (WN(full,4)) (ablation) | GeoPhy · DS1 | MLL: -7111.55 -> -7119.77 | Hurt |
| add LAX to LOO(3), i.e. LOO(3)+ (ablation) | GeoPhy WN(full,4) · DS8 | MLL: -8671.32 -> -8660.48 | Improved |
| add LAX to LOO(3), i.e. LOO(3)+ (ablation) | GeoPhy WN(full,4) · DS7 | MLL: -37350.77 -> -37358.96 | Hurt |
| compare GeoPhy WN(full,4) LAX against CSMC | CSMC · DS1 | MLL: -8306.76 -> -7111.55 | Improved |
| compare GeoPhy WN(full,4) LAX against phi-CSMC | phi-CSMC · DS2 | MLL: -30568.49 -> -26379.48 | Improved |
| compare GeoPhy WN(full,4) LAX against phi-CSMC | phi-CSMC · DS1 | MLL: -7290.36 -> -7111.55 | Improved |
| compare GeoPhy WN(diag,2) LAX against phi-CSMC | phi-CSMC · DS3 | MLL: -33798.06 -> -33823.74 | Hurt |
| compare GeoPhy WN(full,4) LAX against VBPI-GNN (preselected topologies) | VBPI-GNN · DS1 | MLL: -7108.41 -> -7111.55 | Hurt |
Closest papers by meaning
- PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation (NeurIPS 2024 · similarity 0.89)
- Likelihood-free inference of phylogenetic tree posterior distributions (NeurIPS 2026 · similarity 0.89)
- Variational Phylogenetic Inference with Products over Bipartitions (ICML 2025 · similarity 0.88)
- PhyloGFN: Phylogenetic inference with generative flow networks (ICLR 2024 · similarity 0.88)
- Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes (NeurIPS 2026 · similarity 0.88)
- PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders (ICLR 2025 · 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.
