Research map / Bandits and online learning / Online convex optimization and games
Understanding the Role of Feedback in Online Learning with Switching Costs
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 |
|---|---|---|---|
| Add extra observations to bandit feedback, up to Bex = \widetilde{O}(K^{1/3}T^{2/3}) | Online learning with switching costs · Bandit feedback with extra observations | minimax regret: \widetilde{\Theta}(K^{1/3}T^{2/3}) | No clear effect |
| Increase extra observations into the regime Bex = \widetilde{\Omega}(K^{1/3}T^{2/3}) | Online learning with switching costs and bandit feedback · Bandit feedback with extra observations | minimax regret: \widetilde{\Theta}(K^{1/3}T^{2/3}) -> \widetilde{\Theta}(T\sqrt{K/\Bex}) | Helped |
| Increase the total observation budget B | TBD · Online learning with switching costs and total observation budget | minimax regret: \widetilde{\Theta}(T\sqrt{K/B}) | Helped |
| Use bandit feedback rather than choosing feedback type to fit the budget in the high-budget regime | Online learning with switching costs and total observation budget · B = \Omega(K^{1/3}T^{2/3}) | regret | Hurt |
| Distribute observations freely across rounds within a total budget | Online learning with switching costs · Total observation budget B | minimax regret: \widetilde{\Theta}(T\sqrt{K/B}) | No clear effect |
Closest papers by meaning
- Best of Both Worlds: Regret Minimization versus Minimax Play (ICML 2025 · similarity 0.90)
- A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds (NeurIPS 2024 · similarity 0.89)
- Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting (AAAI 2025 · similarity 0.89)
- Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality (NeurIPS 2025 · similarity 0.89)
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback (ICML 2025 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 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.