2018/04/11 by Tatsunori Hashimoto, Steve Yadlowsky, Hashimoto, Tatsunori B. +3
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Algorithms and Data Compression #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms
paper · pdf · doi:10.48550/arxiv.1804.03761
openalex publication_date 2018/04/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We develop an algorithm for minimizing a function using n batched function value measurements at each of T rounds by using classifiers to identify a function's sublevel set. We show that sufficiently accurate classifiers can achieve linear convergence rates, and show that the convergence rate is tied to the difficulty of active learning sublevel sets. Further, we show that the bootstrap is a computationally efficient approximation to the necessary classification scheme. The end result is a computationally efficient derivative-free algorithm requiring no tuning that consistently outperforms other approaches on simulations, standard benchmarks, real-world DNA binding optimization, and airfoil design problems whenever batched function queries are natural.