AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies

Takahiro Mimori, Michiaki Hamada

NeurIPS 2023 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning · 2 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
use wrapped normal 4-d full covariance instead of 2-d diagonal Q(z), LAX (ablation)GeoPhy · DS1MLL: -7126.89 -> -7111.55Improved
use wrapped normal 4-d full covariance instead of 2-d diagonal Q(z), LAX (ablation)GeoPhy · DS2MLL: -26444.84 -> -26379.48Improved
use wrapped normal 4-d full covariance instead of 2-d diagonal Q(z), LAX (ablation)GeoPhy · DS7MLL: -37516.88 -> -37377.86Improved
swap LAX for LOO(3) control variate (WN(full,4)) (ablation)GeoPhy · DS2MLL: -26379.48 -> -26368.44Improved
swap LAX for LOO(3) control variate (WN(full,4)) (ablation)GeoPhy · DS1MLL: -7111.55 -> -7119.77Hurt
add LAX to LOO(3), i.e. LOO(3)+ (ablation)GeoPhy WN(full,4) · DS8MLL: -8671.32 -> -8660.48Improved
add LAX to LOO(3), i.e. LOO(3)+ (ablation)GeoPhy WN(full,4) · DS7MLL: -37350.77 -> -37358.96Hurt
compare GeoPhy WN(full,4) LAX against CSMCCSMC · DS1MLL: -8306.76 -> -7111.55Improved
compare GeoPhy WN(full,4) LAX against phi-CSMCphi-CSMC · DS2MLL: -30568.49 -> -26379.48Improved
compare GeoPhy WN(full,4) LAX against phi-CSMCphi-CSMC · DS1MLL: -7290.36 -> -7111.55Improved
compare GeoPhy WN(diag,2) LAX against phi-CSMCphi-CSMC · DS3MLL: -33798.06 -> -33823.74Hurt
compare GeoPhy WN(full,4) LAX against VBPI-GNN (preselected topologies)VBPI-GNN · DS1MLL: -7108.41 -> -7111.55Hurt

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