AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Learning Sparse Latent Representations with the Deep Copula Information Bottleneck

Aleksander Wieczorek*, Mario Wieser*, Damian Murezzan, Volker Roth

ICLR 2018 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse graphical and tensor models

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
Apply the copula transformation to DIBDIB · Artificial dataI(y;t): approximately 6 -> approximately 11Improved
Apply the copula transformation to DIBDIB · Artificial dataactive latent dimensions: 10 out of 18 dimensions -> two dimensionsImproved
Apply the copula transformation to DIBDIB · Artificial data, test dataI(t;y)Improved
Apply the copula transformation to DIBDIB · Artificial data, reconstructionreconstruction qualityImproved
Apply the copula transformation to DIBDIB · Artificial data with outliersrobustness to outliersImproved
Apply the copula transformation to DIBDIB · Artificial data, training convergenceconvergence speed: around iteration no. 1000Improved
Apply the copula transformation to DIBDIB · Communities and Crimeactive latent dimensions: eight dimensions -> four dimensionsImproved
Apply the copula transformation to DIBDIB · Communities and CrimeI(y;t): p-value of 1.6*10^{-16}Improved
Apply the copula transformation to DIBDIB · Communities and Crime, latent-space structurelatent disentanglementImproved
Replace the copula transformation with mean-zero, unit-variance normalization (ablation)cDIB · Artificial dataI(y;t)Hurt
Replace the beta transformation with a gamma transformation in the experiment (ablation)Artificial data · Artificial dataI(y;t)Improved
Vary the hyperparameter lambda (ablation)cDIB · Communities and Crimelatent disentanglement: 1.79 and 1897.15No clear effect

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