AI Paper Atlas

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

A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning

Yoshihiro Nagano, Shoichiro Yamaguchi, Yasuhiro Fujita, Masanori Koyama

ICML 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Likelihood-free and graphical model estimation · 61 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 hyperbolic rather than Euclidean latent geometryVAE on the synthetic binary tree · Synthetic Binary TreeCorrelation: 0.644 {\scriptstyle \pm .011} -> 0.768 {\scriptstyle \pm .003}Improved
Use hyperbolic rather than Euclidean latent geometryVAE on the noisy synthetic binary tree · Synthetic Binary Tree with noiseCorrelation: 0.550 {\scriptstyle \pm .012} -> 0.590 {\scriptstyle \pm .018}Improved
Use hyperbolic rather than Euclidean latent geometryVAE on binarized MNIST with 2 latent dimensions · MNISTlog-likelihood: -140.45 {\scriptstyle \pm .47} -> -138.61 {\scriptstyle \pm 0.45}Improved
Use hyperbolic rather than Euclidean latent geometryVAE on binarized MNIST with 5 latent dimensions · MNISTlog-likelihood: -105.78 {\scriptstyle \pm .51} -> -105.38 {\scriptstyle \pm 0.61}Improved
Use hyperbolic rather than Euclidean latent geometryVAE on binarized MNIST with 10 latent dimensions · MNISTlog-likelihood: -86.25 {\scriptstyle \pm .52} -> -86.40 {\scriptstyle \pm 0.28}Hurt
Use hyperbolic rather than Euclidean latent geometryVAE on binarized MNIST with 20 latent dimensions · MNISTlog-likelihood: -77.89 {\scriptstyle \pm .36} -> -79.23 {\scriptstyle \pm 0.20}Hurt
Use hyperbolic rather than Euclidean latent geometryVAE trained on Breakout trajectories · Atari 2600 Breakoutcorrelation with cumulative reward: 0.712 -> 0.8460Improved
Use hyperbolic rather than Euclidean geometryProbabilistic word embedding with diagonal variance, 5 dimensions · WordNet nounsMAP: 0.296 {\scriptstyle \pm .006} -> 0.506 {\scriptstyle \pm .017}Improved
Use hyperbolic rather than Euclidean geometryProbabilistic word embedding with diagonal variance, 10 dimensions · WordNet nounsMAP: 0.778 {\scriptstyle \pm .007} -> 0.795 {\scriptstyle \pm .007}Improved
Use hyperbolic rather than Euclidean geometryProbabilistic word embedding with diagonal variance, 20 dimensions · WordNet nounsMAP: 0.894 {\scriptstyle \pm .002} -> 0.897 {\scriptstyle \pm .005}No clear effect
Use hyperbolic rather than Euclidean geometryProbabilistic word embedding with diagonal variance, 50 dimensions · WordNet nounsMAP: 0.942 {\scriptstyle \pm .003} -> 0.975 {\scriptstyle \pm .001}Improved
Use hyperbolic rather than Euclidean geometryProbabilistic word embedding with diagonal variance, 100 dimensions · WordNet nounsMAP: 0.953 {\scriptstyle \pm .002} -> 0.978 {\scriptstyle \pm .002}Improved

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