AI Paper Atlas

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

Evaluating State-of-the-Art Classification Models Against Bayes Optimality

Ryan Theisen, Huan Wang, Lav R. Varshney, Caiming Xiong, richard socher

NeurIPS 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 6 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 the estimated Bayes error to rank datasets with NLL below 1000Glow Bayes-error estimates · MNIST, EMNIST, and SVHN datasets with NLL below 1000ranking agreement with SOTA errorImproved
Increase temperature of the flow-generated dataWide-ResNet and ConvNet · Synthetic MNIST and Fashion-MNISTtest errorHurt
Use harder flow-generated datasets at higher temperatureWide-ResNet and ConvNet · Synthetic MNIST and Fashion-MNISTgap to Bayes errorMixed
Use modern architectures rather than older/simple classifiersSynthetic Fashion-MNIST at temperature 1 · Synthetic Fashion-MNISTtest errorImproved

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