用贝叶斯优化保留搜索信息，提升步长选择效果。
Information Preserving Line Search via Bayesian Optimization
- 基于贝叶斯优化保留函数值与梯度信息
- 在CUTEst测试集上优于当前最优方法
- 理论保证收敛，适合复杂优化问题
线搜索是无约束和边界约束优化问题中迭代优化方法的核心，用于确定每一步的合适步长以实现充分改进。传统线搜索方法依赖迭代区间收缩，每次迭代都会丢弃函数值和梯度等有价值的信息。本文提出一种基于贝叶斯优化的线搜索方法，保留并利用这些被丢弃的信息，以改进步长选择。该方法理论上保证收敛，并在具有挑战性的无约束和边界约束优化问题（来自CUTEst测试集）的实证测试中表现优于当前最优方法。
原文摘要 · Abstract (English)
Line search is a fundamental part of iterative optimization methods for unconstrained and bound-constrained optimization problems to determine suitable step lengths that provide sufficient improvement in each iteration. Traditional line search methods are based on iterative interval refinement, where valuable information about function value and gradient is discarded in each iteration. We propose a line search method via Bayesian optimization, preserving and utilizing otherwise discarded information to improve step-length choices. Our approach is guaranteed to converge and shows superior performance compared to state-of-the-art methods based on empirical tests on the challenging unconstrained and bound-constrained optimization problems from the CUTEst test set.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。