AI Paper Atlas

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

A New Distribution on the Simplex with Auto-Encoding Applications

Andrew Stirn, Tony Jebara, David Knowles

NeurIPS 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Posterior sampling with diffusion guidance · 1 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 fixed-order Kumaraswamy stick-breaking with averaging over sampled orderingsKumar-SB semi-supervised model · MNIST, 600 labels, dim(z)=50classification error: 0.071 ± 0.008 -> 0.018 ± 0.004Improved
Replace fixed-order Kumaraswamy stick-breaking with averaging over sampled orderingsKumar-SB semi-supervised model · SVHN, 1000 labels, dim(z)=50classification error: 0.702 ± 0.011 -> 0.296 ± 0.014Improved
Use MV-Kum. instead of IRGSemi-supervised model · MNIST, 600 labels, dim(z)=50classification error: 0.018 ± 0.004 vs 0.018 ± 0.004No clear effect
Use MV-Kum. instead of IRGSemi-supervised model · SVHN, 1000 labels, dim(z)=50classification error: 0.296 ± 0.014 vs 0.288 ± 0.008No clear effect
Use MV-Kum. instead of SoftmaxSemi-supervised model · MNIST, 600 labels, dim(z)=2classification error: 0.043 ± 0.005 vs 0.042 ± 0.003No clear effect
Use MV-Kum. instead of SoftmaxSemi-supervised model · SVHN, 1000 labels, dim(z)=50classification error: 0.296 ± 0.014 vs 0.300 ± 0.007No clear effect
Use MV-Kum. rather than the stacked M1 + M2 modelSemi-supervised model · SVHN, 1000 labelsclassification error: 0.360 ± 0.001 -> 0.296 ± 0.014Improved
Use dim(z)=50 instead of dim(z)=2MV-Kum. on MNIST · MNIST, 600 labelsclassification error: 0.043 ± 0.005 -> 0.018 ± 0.004Improved
Use dim(z)=0 instead of dim(z)=50MV-Kum. on MNIST · MNIST, 600 labelsclassification error: 0.018 ± 0.004 -> 0.099 ± 0.011Hurt

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