自适应多保真优化与快速学习率
Adaptive multi-fidelity optimization with fast learning rates
AI总结:
本文研究在有限预算下优化局部光滑函数的问题,提出Kometo算法,无需假设函数光滑性或保真度,实现与最优保证相同的学习率,且在无问题依赖参数知识的情况下优于现有方法。
摘要:
在多保真优化中,目标函数的不偏近似成本存在差异。本文研究在有限预算下优化局部光滑函数的问题,其中学习者需在成本与偏差之间进行权衡。我们首先基于成本-偏差函数,在不同保真度假设下证明了简单遗憾的下界。然后提出Kometo算法,在额外对数因子下达到相同速率,无需任何函数光滑性或保真度假设,并改进了之前证明的保证。最后通过实验证明,我们的算法在无问题依赖参数知识的情况下优于现有多保真优化方法。
英文摘要:
In multi-fidelity optimization, biased approximations of varying costs of the target function are available. This paper studies the problem of optimizing a locally smooth function with a limited budget, where the learner has to make a tradeoff between the cost and the bias of these approximations. We first prove lower bounds for the simple regret under different assumptions on the fidelities, based on a cost-to-bias function. We then present the Kometo algorithm which achieves, with additional logarithmic factors, the same rates without any knowledge of the function smoothness and fidelity assumptions, and improves previously proven guarantees. We finally empirically show that our algorithm outperforms previous multi-fidelity optimization methods without the knowledge of problem-dependent parameters.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。