Bandits attack function optimization
Philippe Preux, Rémi Munos, Michal Valko
TLDR
This paper introduces Simultaneous Optimistic Optimization (SOO), a bandit-inspired algorithm for efficient function optimization under budget constraints.
Key contributions
- Introduces Simultaneous Optimistic Optimization (SOO) for budget-constrained function optimization.
- SOO is a deterministic, bandit-inspired algorithm balancing exploration and exploitation via domain partitioning.
- Offers theoretical guarantees on solution quality and demonstrates strong numerical efficiency.
- Validated empirically on the CEC'2014 single objective real-parameter optimization test-suite.
Why it matters
This paper offers a novel, efficient approach to function optimization, a critical task in many fields, especially when computational resources are limited. The SOO algorithm provides both theoretical guarantees and strong empirical performance, making it a valuable tool for practitioners. Its bandit-inspired design effectively tackles the exploration-exploitation dilemma.
Original Abstract
We consider function optimization as a sequential decision making problem under budget constraint. This constraint limits the number of objective function evaluations allowed during the optimization. We consider an algorithm inspired by a continuous version of a multi-armed bandit problem which attacks this optimization problem by solving the tradeoff between exploration (initial quasi-uniform search of the domain) and exploitation (local optimization around the potentially global maxima). We introduce the so-called Simultaneous Optimistic Optimization (SOO), a deterministic algorithm that works by domain partitioning. The benefit of such approach are the guarantees on the returned solution and the numerical efficiency of the algorithm. We present this machine learning approach to optimization, and provide the empirical assessment of SOO on the CEC'2014 competition on single objective real-parameter numerical optimization test-suite.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.