Research map / Bandits and online learning / Online convex optimization and games
Near-Optimal Design of Experiments via Regret Minimization
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 |
|---|---|---|---|
| Algorithm 1 vs uniform sampling | Experimental design · Synthetic k=2p | fE objective: 349.4 -> 53.52 | Helped |
| Algorithm 1 vs Fedorov's exchange | Experimental design · Synthetic k=2p | fE objective: 172.9 -> 53.52 | Helped |
| Algorithm 1 vs Fedorov's exchange | Experimental design · Synthetic k=2p | fG objective: 117.7 -> 90.77 | Helped |
| Algorithm 1 vs weighted sampling | Experimental design · Synthetic k=2p | fT objective: Inf -> 1.19 | Helped |
| Algorithm 1 vs Fedorov's exchange | Experimental design · Synthetic k=2p | fD objective: 5.52 -> 4.72 | No clear effect |
| Algorithm 1 vs Fedorov's exchange on running time | Algorithm 1 · Synthetic k=2p, fG | running time (s): 8893 -> < 1 | Helped |
| Algorithm 1 vs Fedorov's exchange | Experimental design · Minnesota wind, fV design | fV objective: 10.0 -> 10.8 | No clear effect |
| Algorithm 1 vs Fedorov's exchange | Experimental design · Minnesota wind, fV design | MSE: 0.86 -> 0.72 | Helped |
| Algorithm 1 vs Fedorov's exchange | Experimental design · Minnesota wind, fG design | MSE: 0.78 -> 0.76 | Helped |
| Algorithm 1 vs uniform sampling | Experimental design · Minnesota wind, fG design | fG objective: 3093 -> 29.2 | Helped |
| Algorithm 1 vs weighted sampling | Experimental design · Minnesota wind, fV design | fV objective: 21.4 -> 10.8 | Helped |
| increase k from 2p to 3p | Algorithm 1 · Synthetic | fE objective: 53.52 -> 41.53 | Helped |
Closest papers by meaning
- Sequential Bayesian Experimental Design with Variable Cost Structure (NeurIPS 2020 · similarity 0.87)
- High-dimensional Experimental Design and Kernel Bandits (ICML 2021 · similarity 0.87)
- Stronger Neyman Regret Guarantees for Adaptive Experimental Design (ICML 2025 · similarity 0.86)
- PASOA- PArticle baSed Bayesian Optimal Adaptive design (ICML 2024 · similarity 0.85)
- Nesting Particle Filters for Experimental Design in Dynamical Systems (ICML 2024 · similarity 0.84)
- The Non-linear $F$-Design and Applications to Interactive Learning (ICML 2024 · similarity 0.84)
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.