AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Contrastive Predictive Coding Done Right for Mutual Information Estimation

Jongha Jon Ryu, Pavan Yeddanapudi, Xiangxiang Xu, Gregory W. Wornell

ICLR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Inductive bias and minimal representations

Read the paper

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 an anchor class (nu=1) to InfoNCE (ablation)InfoNCE for SSL · CIFAR-100 linear probe, ResNet-18top-1 accuracy: 65.98 -> 65.74No clear effect
add an anchor class to InfoNCE for MI estimationInfoNCE · MI benchmark (Gaussian, MNIST, BERT text)MI estimation bias and varianceImproved
use large K (K=B-1) instead of K=1 (JS plug-in) (ablation)InfoNCE-anchor · MNIST and text MI estimationMI estimation accuracyImproved
use large K instead of K=1 (JS) in SSL pretraining (ablation)contrastive objective · CIFAR-100 linear probe, top-1top-1 accuracy: 61.69 -> 65.74Improved
replace log score with spherical proper scoring rule (ablation)InfoNCE-anchor · MI estimationMI estimation accuracyHurt
replace log score with spherical proper scoring rule (ablation)InfoNCE-anchor · CIFAR-100 linear probe, top-1top-1 accuracy: 65.74 -> 4.33Hurt
replace log score with chi-squared scoring rule (ablation)InfoNCE-anchor · CIFAR-100 linear probe, top-1top-1 accuracy: 65.74 -> 65.59No clear effect
use InfoNCE-anchor plug-in estimator for protein interaction prediction instead of other variational estimatorsPMI estimator on ProtTrans5 embeddings · OmniPath kinase-target and ligand-receptorROC predictionImproved

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