AI Paper Atlas

Research map / Optimization / Optimizers

Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization

Qing Guo, Junya Chen, Dong Wang, Yuewei Yang, Xinwei Deng, Jing Huang, Lawrence Carin, Fan Li, Chenyang Tao

NeurIPS 2022 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 10 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
use FDV (FLO-derived) objective instead of InfoNCE for contrastive pretrainingSimCLR · CIFAR linear probingsample efficiency (batch size for equal accuracy): FlatCLR-32 vs SimCLR-256 (8x)Improved
share one network with two heads for g(x,y) and u(x,y) rather than separate critics (ablation)FLO · 20-D Gaussian rho=0.5MI estimation learning speedImproved
use deeper critic MLP (2, 3, 6 layers) (ablation)FLO · Gaussian MI estimationconvergence speed and MI estimateMixed
replace NWJ/InfoNCE with FLO as MI objective for design optimizationBayesian optimal experiment design · BOED static and dynamic designsexpected information gainImproved
add FLO-based regularizer to the empirical risk (Meta-FLO) versus MAMLmeta-learning · few-shot regression benchmarkadaptation performanceImproved
tune alpha in alpha-InfoNCEalpha-InfoNCE · Gaussian MI estimationbias-varianceNo 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