Research map / Learning theory and algorithms / Sample complexity
Finite Sample Analysis Of Dynamic Regression Parameter Learning
Mark Kozdoba, Edward Moroshko, Shie Mannor, Koby Crammer
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 |
|---|---|---|---|
| Increase number of time steps T | STVE · Synthetic LDS (n=5, sigma^2=0.5, eta^2=2, 150 runs) | variance estimation error | Improved |
| Use adaptive models (MLE, STVE, OG) instead of stationary regression | load forecasting · Electricity load vs temperature, train half | daily squared prediction error | Improved |
| Use adaptive models instead of stationary regression | load forecasting · Electricity load vs temperature, test half | daily squared prediction error | Improved |
| Learn Kalman filter variances with STVE instead of MLE | Kalman filter dynamic regression · Electricity load vs temperature | daily squared prediction error | No clear effect |
| Use Kalman filter methods (MLE, STVE) instead of online gradient (OG) | dynamic regression forecaster · Electricity load vs temperature | daily squared prediction error | Improved |
Closest papers by meaning
- Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces (NeurIPS 2022 · similarity 0.85)
- On Low-rank Trace Regression under General Sampling Distribution (JMLR 2022 · similarity 0.85)
- Optimal Linear Regression Without a Variance (NeurIPS 2026 · similarity 0.85)
- Error Bounds for Gaussian Process Regression Under Bounded Support Noise with Applications to Safety Certification (AAAI 2025 · similarity 0.84)
- Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control (NeurIPS 2025 · similarity 0.83)
- On the Benefits of Active Data Collection in Operator Learning (ICML 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.
