Research map / Learning theory and algorithms / Prediction and decision losses
Distributionally Robust Local Non-parametric Conditional Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DRCME instead of k-NN | conditional mean estimation · MNIST digit estimation N=50 | accuracy (%): 24 -> 36 | Helped |
| Use DRCME instead of BertEtAl robust k-NN | conditional mean estimation · MNIST digit estimation N=500 | accuracy (%): 67 -> 71 | Helped |
| Use DRCME instead of Nadaraya-Watson | conditional mean estimation · MNIST digit estimation N=100 | accuracy (%): 38 -> 46 | Helped |
| Use DRCME instead of Nadaraya-Watson | conditional mean estimation · MNIST digit estimation N=500 | RMSE: 1.32 -> 1.41 | Hurt |
| Use DRCME instead of k-NN and BertEtAl | conditional mean estimation · Synthetic data near density jump x0=0.3 | mean absolute error | Helped |
| Use DRCME instead of Nadaraya-Watson far from the jump point | conditional mean estimation · Synthetic data | mean absolute error | Hurt |
| Use DRCME instead of Nadaraya-Watson on adversarially corrupted test images | conditional mean estimation · MNIST corrupted images N=100 | estimate stability | Helped |
Closest papers by meaning
- Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.86)
- A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models (ICML 2025 · similarity 0.86)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.85)
- Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization (ICLR 2025 · similarity 0.85)
- Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation (ICLR 2025 · similarity 0.85)
- Adversarial Robustness of Nonparametric Regression (NeurIPS 2025 · similarity 0.85)
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.