Research map / Bandits and online learning / Multi-armed bandits
The Multi-fidelity Multi-armed Bandit
Kirthevasan Kandasamy, Gautam Dasarathy, Barnabas Poczos, Jeff Schneider
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 |
|---|---|---|---|
| Use multi-fidelity UCB (play cheap low fidelities to eliminate bad arms) instead of single-fidelity UCB | MF-UCB vs UCB · Synthetic bandit simulations (Gaussian and Bernoulli problems) | cumulative pseudo-regret vs capital | Improved |
| Replace classical UCB's uniform highest-fidelity play with fidelity switching (play cheaper fidelities for suboptimal arms) | MF-UCB · Synthetic problems, per-fidelity play counts | number of plays per fidelity | Improved |
| Lower bound: MF-UCB matches the lower bound on arms in the set K_m^1 but may be loose on arms in K_m^2 | MF-UCB · Theoretical regret analysis | regret vs lower bound | Mixed |
| Fidelity-switching threshold gamma_m set by psi^{-1}(cost ratio * psi(zeta_m)) | MF-UCB · Theoretical analysis | regret bound | No clear effect |
Closest papers by meaning
- Multi-Fidelity Multi-Armed Bandits Revisited (NeurIPS 2023 · similarity 0.91)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.88)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.88)
- Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits (ICML 2025 · similarity 0.88)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.88)
- Leveraging (Biased) Information: Multi-armed Bandits with Offline Data (ICML 2024 · similarity 0.87)
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.
