Research map / Bandits and online learning / Online convex optimization and games
Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 sample size from 200 to 2000 | nCor|Delta| · Simulated heteroscedastic examples E1-E4 | detection power | Helped |
| reduce sample size to N=30-150 | nCor|Delta| · Simulated data, Appendix E | detection power | Hurt |
| increase dimension of x (M up to 10) | nCor|Delta| · Multivariate simulated examples | detection power | Hurt |
| increase sample size in multivariate case | nCor|Delta| · Multivariate simulated examples | detection power | Helped |
| change x distribution (uniform, normal, exponential) and R2 (0, 0.4, 0.8) | nCor|Delta| · Simulated examples E1-E4 | detection power | No clear effect |
| use nCor|Delta| instead of Park test | heteroscedasticity detection · Examples 3 and 4 | detection of heteroscedasticity | Helped |
| use nCor|Delta| instead of White test (polynomial degree up to 15) | heteroscedasticity detection · Example 3 with normal x | required model complexity | Helped |
| increase R2 from 0 to 0.8 | dCor and RDC · Examples E1-E4 | sensitivity to heteroscedasticity | Hurt |
| use nCor|Delta| instead of MI and MIC | association measurement · Examples E1-E4 | separating functional from nonfunctional dependence | Helped |
| use nCor instead of nCor|Delta| for heteroscedasticity | association measure · Examples E1-E4 | heteroscedasticity sensitivity | Hurt |
| add x-noise (horizontal) to functional dataset D2 | nCor|Delta| · Reshef datasets D1-D8 with noise, N=10000 | heteroscedasticity detected | Mixed |
| remove isolated extreme-x outlier points before computing the statistic | nCor|Delta| · Small noise, extreme R2 with outliers, Appendix E | type I error | Helped |
Closest papers by meaning
- Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems (NeurIPS 2021 · similarity 0.93)
- Online Control of Unknown Time-Varying Dynamical Systems (NeurIPS 2021 · similarity 0.89)
- Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator (ICLR 2025 · similarity 0.86)
- Finite Time Logarithmic Regret Bounds for Self-Tuning Regulation (ICML 2024 · similarity 0.85)
- Infinite-Horizon Distributionally Robust Regret-Optimal Control (ICML 2024 · similarity 0.85)
- Maximizing the Value of Predictions in Control: Accuracy Is Not Enough (NeurIPS 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.