Research map / Learning theory and algorithms / Prediction and decision losses
Deep Neural Expected Shortfall Regression with Tail-Robustness
Myeonghun Yu, Kean Ming Tan, Huixia Judy Wang, Wen-Xin Zhou
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 Huberized robust loss (DRES) instead of least squares (DES) for the second-step ES regression (ablation) | deep two-step ES estimator · Simulation, heavy-tailed t errors (n=4,096, alpha=0.1) | MSPE | Improved |
| use Huberized robust loss (DRES) instead of least squares (DES) (ablation) | deep two-step ES estimator · Simulation, normal errors (n=4,096, alpha=0.1) | MSPE | Improved |
| use DNN-based estimators instead of local linear ES estimator (LLES) | conditional ES regression · Simulation, 8-dim heteroscedastic model (n=4,096, alpha=0.1) | MSPE | Improved |
| estimate the first-step quantile function instead of using the true one (DRES vs oracle-DRES) (ablation) | two-step robust ES estimator · Simulation, n from 2,048 to 9,216 (alpha=0.1) | MSPE | No clear effect |
Closest papers by meaning
- Linear Hypothesis Testing in High-Dimensional Expected Shortfall Regression with Heavy-Tailed Errors (JMLR 2025 · similarity 0.89)
- Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel (ICLR 2020 · similarity 0.84)
- On the Asymptotic Distribution of the Minimum Empirical Risk (ICML 2024 · similarity 0.83)
- Quantile-Regression-Ensemble: A Deep Learning Algorithm for Downscaling Extreme Precipitation (AAAI 2024 · similarity 0.82)
- Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows (NeurIPS 2025 · similarity 0.82)
- Neural Conditional Probability for Uncertainty Quantification (NeurIPS 2024 · similarity 0.82)
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.
