Research map / Learning theory and algorithms / Kernels and regression theory
Optimal Functional Bilinear Regression with Two-dimensional Functional Covariates via Reproducing Kernel Hilbert Space
Dan Yang, Jianlong Shao, Haipeng Shen, Hongtu Zhu
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 iGCV instead of CV for tuning parameter selection (ablation) | FBLR · Simulation Setting 1 | excess prediction risk | No clear effect |
| use estimated covariances instead of true covariances (ablation) | FBLR · Simulation Setting 1 | excess prediction risk | No clear effect |
| initialize with Ridge, PFPCR or MFPCR (ablation) | FBLR · Simulation Setting 1 (r_c=1) | excess prediction risk | No clear effect |
| larger covariance smoothness r_c (ablation) | FBLR · Simulation Setting 1 | excess prediction risk | Improved |
| FBLR penalized estimator instead of 2D-FPCR (PFPCR, MFPCR) with oracle rmax=4 | PFPCR/MFPCR · Simulation Setting 1 | excess prediction risk | Improved |
| increase max PCs from 4 to 8 (ablation) | PFPCR/MFPCR · Simulation Setting 1 | excess prediction risk | Hurt |
| increase max PCs from 4 to 8 under misalignment (ablation) | PFPCR/MFPCR · Simulation Settings 3-4 | excess prediction risk | Improved |
| use FBLR instead of FLR+TPK | FLR+TPK · Simulation Settings 1-4 | excess prediction risk | Improved |
| apply FBLR twice with deflation (R=2) instead of once (ablation) | FBLR · Simulation Setting 5 | excess prediction risk | Mixed |
| apply FBLR twice with deflation (R=2) instead of once (ablation) | FBLR · Simulation Setting 6 (non-low-rank coefficient) | excess prediction risk | Improved |
| use FBLR instead of 1D FLR+ave on hour-averaged temperature | FLR+ave · Canadian weather (leave-one-out) | out-of-sample squared error | Improved |
Closest papers by meaning
- Functional Linear Regression with Mixed Predictors (JMLR 2022 · similarity 0.89)
- Nonlinear function-on-function regression by RKHS (JMLR 2026 · similarity 0.88)
- Statistical Optimality of Divide and Conquer Kernel-based Functional Linear Regression (JMLR 2024 · similarity 0.86)
- Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions (NeurIPS 2025 · similarity 0.83)
- On Hypothesis Transfer Learning of Functional Linear Models (ICML 2024 · similarity 0.83)
- Computational Efficiency under Covariate Shift in Kernel Ridge Regression (NeurIPS 2025 · similarity 0.83)
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.
