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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use the estimated Bayes error to rank datasets with NLL below 1000 | Glow Bayes-error estimates · MNIST, EMNIST, and SVHN datasets with NLL below 1000 | ranking agreement with SOTA error | Improved |
| Increase temperature of the flow-generated data | Wide-ResNet and ConvNet · Synthetic MNIST and Fashion-MNIST | test error | Hurt |
| Use harder flow-generated datasets at higher temperature | Wide-ResNet and ConvNet · Synthetic MNIST and Fashion-MNIST | gap to Bayes error | Mixed |
| Use modern architectures rather than older/simple classifiers | Synthetic Fashion-MNIST at temperature 1 · Synthetic Fashion-MNIST | test error | Improved |
Closest papers by meaning
- Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification (ICLR 2023 · similarity 0.88)
- Optimal Binary Classification Beyond Accuracy (NeurIPS 2022 · similarity 0.88)
- Demystifying the Optimal Performance of Multi-Class Classification (NeurIPS 2023 · similarity 0.88)
- SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning (ICML 2024 · similarity 0.85)
- Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification (NeurIPS 2026 · similarity 0.85)
- Provably Reliable Classifier Guidance via Cross-Entropy Control (NeurIPS 2026 · similarity 0.84)
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.
