AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Gaussian Lower Bound for the Information Bottleneck Limit

Amichai Painsky, Naftali Tishby

JMLR 2018 · Learning theory and algorithms › Sample complexity · approach: Generalization and limits under data constraints · 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
replace naive separate Gaussianization with mixture-aware custom Gaussianizationseparate Gaussianization lower bound · Univariate Gaussian mixture exampleGaussian lower bound on MI (bits): 0.0628 -> 0.204Improved
use AGCE instead of the custom mixture-aware GaussianizationGaussian lower bound on MI · Univariate Gaussian mixture exampleGaussian lower bound on MI (bits): 0.204 -> 0.411Improved
use separate Gaussianization of ACE output instead of AGCEGaussian lower bound on MI · Univariate Gaussian mixture exampleGaussian lower bound on MI (bits): 0.411 -> 0.389No clear effect
replace separate Gaussianization with bi-terminal Gaussianization of ACE outputmultivariate Gaussian lower bound · Multivariate toy models, d>5 with KCCAGaussian lower bound on MIImproved
use KCCA instead of ACE for dimension above 5multivariate Gaussian lower bound · Multivariate toy modelsGaussian lower bound on MIHurt
use the Gaussian lower bound instead of GIB applied directly to non-monotonically scrambled dataIB curve lower bound · Exponential model, IB curveIB curve lower boundImproved

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