Research map / Bandits and online learning / Online convex optimization and games
Non-stationary Online Learning with Memory and Non-stochastic Control
Peng Zhao, Yu-Hu Yan, Yu-Xiang Wang, Zhi-Hua Zhou
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 |
|---|---|---|---|
| add meta-base switching-cost-regularized loss (Scream) versus OGD at small regularizer alpha=0.1 | Scream · OCO with switching cost (T=50000, d=10) | overall loss | No clear effect |
| use Scream versus Ader and OGD at medium regularizer alpha=1 | Scream · OCO with switching cost (T=50000, d=10) | overall loss | Improved |
| use Scream versus OGD at large regularizer alpha=2 | Scream · OCO with switching cost (T=50000, d=10) | overall loss | No clear effect |
| ignore switching cost (Ader) at large regularizer alpha=2 | Ader · OCO with switching cost (T=50000, d=10) | overall loss | Hurt |
| use Scream.Control versus OGD.Control and Ader.Control | Scream.Control · Time-varying LDS, gradual change | cumulative cost | Improved |
| use Scream.Control versus OGD.Control and Ader.Control | Scream.Control · Time-varying LDS, abrupt change | cumulative cost | Improved |
| use Scream.Control versus OGD.Control and Ader.Control | Scream.Control · Inverted pendulum | cumulative cost | Improved |
Closest papers by meaning
- Online Non-stochastic Control with Partial Feedback (JMLR 2023 · similarity 0.94)
- Efficient Methods for Non-stationary Online Learning (NeurIPS 2022 · similarity 0.93)
- Making Non-Stochastic Control (Almost) as Easy as Stochastic (NeurIPS 2020 · similarity 0.91)
- Dynamic Regret in Online Convex Optimization with Indicator Switching Costs (NeurIPS 2026 · similarity 0.90)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.89)
- Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · similarity 0.89)
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.
