Research map / Learning theory and algorithms / Sample complexity
Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers
JULIAN KATZ-SAMUELS, Blake Mason, Kevin Jamieson, Rob Nowak
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 GRAILS instead of GP-UCB and uniform sampling while varying RBF kernel width sigma | GRAILS · Random 2d RKHS functions, 400-point grid | samples to simple regret below 0.01 | Improved |
| add pairwise-constraint prior knowledge to GRAILS and OFUL | GRAILS · 1d RKHS, n=250, RBF sigma = 0.075 | samples to simple regret 0.005 | Improved |
| use GRAILS instead of OFUL | GRAILS · Random 2d RKHS functions | samples to simple regret | Improved |
| use GRAILS instead of OFUL on convex function class | GRAILS · Convex functions, 300-point grid, 30 trials | samples to epsilon-accurate solution | Improved |
| use GRAILS instead of uniform sampling as epsilon decreases | GRAILS · Convex functions, 300-point grid | samples to epsilon-accurate solution | Improved |
Closest papers by meaning
- Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability (NeurIPS 2024 · similarity 0.85)
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · similarity 0.85)
- Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization (NeurIPS 2024 · similarity 0.84)
- The Non-linear $F$-Design and Applications to Interactive Learning (ICML 2024 · similarity 0.84)
- Provably Efficient Interactive-Grounded Learning with Personalized Reward (NeurIPS 2024 · similarity 0.84)
- Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback (NeurIPS 2026 · 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.
