Research map / Learning theory and algorithms / Kernels and regression theory
Regularized Modal Regression on Markov-Dependent Observations: A Theoretical Assessment
Tieliang Gong, Yuxin Dong, Hong Chen, Wei Feng, Bo Dong, Chen Li
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 |
|---|---|---|---|
| Apply RMR to stationary Markov-dependent observations with non-zero absolute spectral gap | RMR · Markov-dependent observations | excess generalization risk: (2\gamma_a - \gamma_a^2) ^{-\frac{\theta}{\beta}} m^{-\theta} | Mixed |
| Replace independent observations with Markov-dependent observations | RMR · Markov-dependent observations versus i.i.d. observations | learning rate: (2\gamma_a -\gamma_a^2)^{-\frac{1}{5}} | Hurt |
| Measure hypothesis-space capacity with empirical covering numbers rather than Rademacher complexity | RMR theoretical analysis · i.i.d. observations | learning rate: m^{-\frac{1}{7}} -> m^{-\frac{1}{5}} | Improved |
Closest papers by meaning
- A Statistical Learning Approach to Modal Regression (JMLR 2020 · similarity 0.90)
- Efficient Analytic Uncertainty Quantification for Multimodal Regression (NeurIPS 2026 · similarity 0.85)
- Sparse Variational Student-t Processes (AAAI 2024 · similarity 0.84)
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.84)
- Beyond the Norms: Detecting Prediction Errors in Regression Models (ICML 2024 · similarity 0.84)
- TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression (ICML 2024 · similarity 0.84)
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.
