AI Paper Atlas

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

Deep Variational Multivariate Information Bottleneck - A Framework for Variational Losses

Eslam Abdelaleem, Ilya Nemenman, K. Michael Martini

JMLR 2025 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Structured latent VAEs · 12 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
add MINE-based mutual information decoder (DVSIB) instead of beta-VAEbeta-VAE · Noisy MNIST Y view (linear SVM)accuracy %: 96.3 -> 97.8Improved
add beta trade-off weighting to DVCCA (ablation)DVCCA · Noisy MNIST Y view (linear SVM)accuracy %: 89.6 -> 95.4Improved
add beta weighting to DVCCA with joint input (ablation)jDVCCA · Noisy MNIST joint [X,Y] (linear SVM)accuracy %: 92.5 -> 96.7Improved
add private variables to beta-DVCCA (ablation)beta-DVCCA · Noisy MNIST Y view (linear SVM)accuracy %: 95.4 -> 95.5No clear effect
add private variables to DVSIB (ablation)DVSIB · Noisy MNIST Y view (linear SVM)accuracy %: 97.8 -> 97.8No clear effect
add private variables to DVCCA (ablation)DVCCA · Noisy MNIST Y view (linear SVM)accuracy %: 89.6 -> 92.1Improved
use DVIB (compress Y, predict X) instead of PCAPCA · Noisy MNIST Y view (linear SVM)accuracy %: 90.5 -> 90.4No clear effect
use DVSIB instead of beta-VAE as training set growsbeta-VAE · Noisy MNIST Y view, k_Z=64, sample-size scalinglog-log slope: 0.196 ± 0.013 -> 0.345 ± 0.007Improved
use joint [X,Y] input with beta-VAE-style DVCCA-pbeta-DVCCA-private · Noisy MNIST Y view with private variablesaccuracy %: 95.5 -> 92.7Hurt

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