AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

All your loss are belong to Bayes

Christian Walder, Richard Nock

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking-based loss optimization · 4 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 ISGP (monotone source prior) instead of GP prior for linkLinkgistic · MNIST/Fashion-MNIST generalised linear modelstest AUC: 99.1 % -> 99.2 %Improved
learn the link with ISGP-Linkgistic instead of fixed logistic linklogistic regression · Fashion-MNISTtest AUC: 98.5% -> 99.2 %Improved
learn the link with ISGP-Linkgistic instead of fixed logistic linklogistic regression · MNISTtest AUC: 99.9% -> 99.9 %No clear effect
use ISGP-Linkgistic instead of BregmanTronlink-learning GLM · Fashion-MNISTtest AUC: 97.9% -> 99.2 %Improved
use ISGP-Linkgistic instead of SLIsotronlink-learning GLM · MNISTtest AUC: 94.6% -> 99.9 %Improved
use ISGP prior instead of GP prior for isotonic regressionregression model · auto-mpg displacement, Small trainmean test NLL: 871.0 -> 849.4Improved
use ISGP prior instead of GP prior for isotonic regressionregression model · auto-mpg weight, Small trainmean test NLL: 777.2 -> 770.7Improved
use ISGP prior instead of GP prior for isotonic regressionregression model · auto-mpg acceleration, Small trainmean test NLL: 2173.3 -> 2216.8Hurt
use ISGP prior instead of GP prior with Large training setregression model · auto-mpg weight, Large trainmean test NLL: 735.5 -> 750.7Hurt
use ISGP prior instead of GP prior with Large training setregression model · auto-mpg displacement, Large trainmean test NLL: 788.1 -> 780.6Improved
use PAVA instead of ISGP on small training setisotonic regression · auto-mpg weight, Small trainmean test NLL: 770.7 -> 835.8Hurt
use PAVA instead of ISGP on large training setisotonic regression · auto-mpg power, Large trainmean test NLL: 763.9 -> 755.5Improved

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