AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition

Meena Jagadeesan, Michael Jordan, Jacob Steinhardt, Nika Haghtalab

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias

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
Improve the representation from the trivial to the informative representationCompeting predictors · Binary classification, simple mathematical exampleequilibrium social loss: 0 -> 0.1Hurt
Improve representation quality by varying per-representation Bayes riskCompeting predictors · Stylized binary classification, single representationequilibrium social lossMixed
Improve representation quality by reducing representation noiseCompeting predictors · Stylized binary classification, Gaussian mixtureequilibrium social lossMixed
Improve representation quality by increasing representation dimensionCompeting predictors · Stylized binary classification, synthetic dataequilibrium social lossMixed
Improve representation quality by varying per-representation Bayes riskLinear predictors with noisy user decisions · Synthetic binary classificationequilibrium social lossMixed
Improve representation quality by reducing representation noiseLinear predictors with noisy user decisions · Synthetic binary classification, Gaussian mixtureequilibrium social lossMixed
Improve representation quality by increasing representation dimensionLinear predictors with noisy user decisions · Synthetic binary classificationequilibrium social lossMixed
Use VGG16 rather than AlexNet representationsCompeting linear predictors · CIFAR-10 binary classification, m = 3equilibrium social lossMixed
Use AlexNet rather than ResNet50 representationsCompeting linear predictors · CIFAR-10 binary classification, m = 5 and m = 8equilibrium social lossMixed
Use ResNet50 rather than AlexNet representationsCompeting linear predictors · CIFAR-10 binary classification, m = 3 and m = 4equilibrium social lossMixed
Use ResNet18 rather than VGG16 representationsCompeting linear predictors · CIFAR-10 10-class classificationequilibrium social lossMixed
Use VGG16 rather than AlexNet representationsCompeting linear predictors · CIFAR-10 10-class classification, m = 3equilibrium social lossMixed

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