Research map / Learning theory and algorithms / Kernels and regression theory
Calibrated Reliable Regression using Maximum Mean Discrepancy
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 MMD distribution matching after heteroscedastic NLL training | HNN regression model · Metro-traffic, Bike-sharing, Pickups, PM2.5, Air-quality; Power Plant, Protein Structure, Naval Propulsion, Wine | ECPE: Metro-traffic: 0.032$\pm$0.002 -> 0.017$\pm$0.001; Bike-sharing: 0.027$\pm$0.003 -> 0.006$\pm$0.001; Pickups: 0.018$\pm$ | Helped |
| Use MMD distribution matching after heteroscedastic NLL training | HNN regression model · Metro-traffic, Bike-sharing, Pickups, PM2.5, Air-quality | RMSE: Metro-traffic: 508.9$\pm$1.288 -> 545.5$\pm$4.225; Bike-sharing: 37.60$\pm$0.355 -> 37.93$\pm$0.334; Pickups: 325.9$\pm$ | Mixed |
| Use MMD distribution matching after heteroscedastic NLL training | HNN regression model · Power Plant, Protein Structure, Naval Propulsion, Wine | RMSE: Power Plant: 3.843$\pm$0.165 -> 3.819$\pm$0.112; Protein Structure: 4.337$\pm$0.021 -> 4.556$\pm$0.012; Naval Propulsion | Mixed |
Closest papers by meaning
- Accurate Uncertainties for Deep Learning Using Calibrated Regression (ICML 2018 · similarity 0.90)
- A Large-Scale Study of Probabilistic Calibration in Neural Network Regression (ICML 2023 · similarity 0.88)
- Reassessing How to Compare and Improve the Calibration of Machine Learning Models (ICLR 2025 · similarity 0.88)
- Better Uncertainty Calibration via Proper Scores for Classification and Beyond (NeurIPS 2022 · similarity 0.88)
- Beyond the Norms: Detecting Prediction Errors in Regression Models (ICML 2024 · similarity 0.87)
- The Minimax Rate of Second-Order Calibration (NeurIPS 2026 · similarity 0.86)
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.