AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Diverse Dictionary Learning

Yujia Zheng, Zijian Li, Shunxing Fan, Andrew Gordon Wilson, Kun Zhang

ICLR 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation · 0 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 dependency (Jacobian) sparsity to FactorVAEFactorVAE · Shapes3DDCI: 0.484 -> 0.575Improved
add dependency sparsity to FactorVAEFactorVAE · MPI3DFactorVAE score: 0.599 -> 0.639Improved
add dependency sparsity to EncDiffEncDiff · Shapes3DDCI: 0.901 -> 0.947Improved
add dependency sparsity to EncDiffEncDiff · Cars3DFactorVAE score: 0.779 -> 0.756Hurt
add dependency sparsity to DisCoDisCo · Cars3DFactorVAE score: 0.727 -> 0.789Improved
add dependency sparsity to DisCoDisCo · Shapes3DDCI: 0.710 -> 0.712No clear effect
add latent sparsity (L1 on Z) to FactorVAE (ablation)FactorVAE · Cars3DFactorVAE score: 0.708 -> 0.501Hurt
add latent sparsity to FactorVAE (ablation)FactorVAE · MPI3DFactorVAE score: 0.599 -> 0.440Hurt
add latent sparsity to EncDiff (ablation)EncDiff · Shapes3DFactorVAE score: 0.9999 -> 0.967Hurt
add latent sparsity to DisCo (ablation)DisCo · MPI3DFactorVAE score: 0.396 -> 0.308Hurt
replace latent sparsity with dependency sparsity (ablation)generative disentanglement models · Shapes3D/Cars3D/MPI3DFactorVAE score / DCIImproved
data satisfying Sufficient Diversity vs fully dense dependencies (ablation)VAE with dependency sparsity · syntheticMCCImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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