Research map / Learning theory and algorithms / Kernels and regression theory
Deep Neural Network Regression with Functional Covariates
Hang Zhou, Ju-Sheng Hong, Xiucai Ding, Jane-Ling Wang
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 intermediate input resolution (3-6 h bins) instead of very fine or very coarse bins (ablation) | DNN (2x32 MLP) · UK household electricity | MSE | Improved |
| use 20 bins instead of very few or many bins (ablation) | DNN (2x32 MLP) · NHANES physical activity | MSE | Improved |
| use FPCA representation explaining 90% of variance instead of lower or higher FVE (ablation) | DNN (2x32 MLP) · UK electricity and NHANES | MSE, 1-AUC | Improved |
| use very high input dimension (many bins or FPC scores) (ablation) | DNN (2x32 MLP) · UK electricity and NHANES | MSE | Hurt |
| use DNN instead of linear model on nonlinear synthetic cases | DNN · synthetic functional regression (6 cases) | prediction error | Improved |
| use FPCA instead of binning at comparable dimensions (ablation) | DNN · synthetic and real data | prediction error | Improved |
Closest papers by meaning
- Nonlinear functional regression by functional deep neural network with kernel embedding (JMLR 2025 · similarity 0.89)
- Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate (ICML 2025 · similarity 0.87)
- Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression (ICLR 2025 · similarity 0.86)
- Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression (ICLR 2025 · similarity 0.86)
- High-Dimensional Analysis for Generalized Nonlinear Regression: From Asymptotics to Algorithm (AAAI 2024 · similarity 0.85)
- Neural Networks Perform Sufficient Dimension Reduction (AAAI 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.
