AI Paper Atlas

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

Geodesic Slice Sampling on the Sphere

Michael Habeck, Mareike Hasenpflug, Shantanu Kodgirwar, Daniel Rudolf

JMLR 2025 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Hamiltonian Monte Carlo · 16 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 geoSSS (reject) instead of geoSSS (shrink)geodesic slice sampling · Rigid registration AKiterations to 100% success: 1500 -> 200Improved
use geoSSS instead of RWMH or HMCMCMC sampler · Rigid registration AKsuccess rate: 3-7% -> 100%Improved
use geoSSS (shrink) over geoSSS (reject) when measured by computation timegeodesic slice sampling · Rigid registration AKsuccess vs computation timeImproved
use geoSSS instead of RWMH and HMC on multimodal targetMCMC sampler · vMF mixture d=10 K=5 kappa=100mode visit KL divergenceImproved
use geoSSS (reject) instead of shrinkgeodesic slice sampling · vMF mixture kappa 50 to 500relative ESSImproved
use geoSSS (reject) instead of shrinkgeodesic slice sampling · vMF mixture kappa 50 to 500rejections per step: 17 -> 60 vs 4 -> 6Hurt
increase concentration kappa from 50 to 500 (ablation)all samplers · vMF mixture d=10 K=5relative ESSHurt
use geoSSS (shrink) instead of mixture-MH tuned alphasampler · vMF mixtureKL divergence and ESSNo clear effect
use HMC instead of geoSSSsampler · Curved vMF d=5 kappa 500relative ESSImproved
increase dimension from 3 to 24 (ablation)geoSSS and RWMH · Curved vMF kappa=500relative ESSHurt
use geoSSS or HMC instead of RWMHsampler · Curved vMF 2-sphere kappa=500ACF, KL, jump distanceImproved

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