arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.05442cs.LGcs.AI
收藏

函数图模型:结构赋能离线数据驱动优化

Functional Graphical Models: Structure Enables Offline Data-Driven Optimization

UC Berkeley(加州大学伯克利分校);Genentech(基因泰克)

Jakub Grudzien Kuba, Masatoshi Uehara, Pieter Abbeel, Sergey Levine

AI总结:

本文提出函数图模型(FGMs),通过将高维优化问题分解为子问题实现样本高效的离线数据驱动优化,在数据覆盖不足时仍能获得近乎最优设计。

摘要:

虽然机器学习模型通常被训练来解决预测问题,但我们可能经常希望将它们用于优化问题。例如,给定一个蛋白质数据集及其相应的荧光水平,我们可能希望优化出具有最高可能荧光水平的新蛋白质。这种数据驱动优化(DDO)带来了标准预测问题之外的一系列挑战,因为我们需要模型能够成功预测比训练集中最佳设计更好的新设计的性能。从理论上讲,现有方法何时能比仅选择数据集中最佳设计的朴素方法表现更好尚不清楚。在本文中,我们研究了结构如何实现样本高效的数据驱动优化。为了形式化结构的概念,我们引入了函数图模型(FGMs),并从理论上展示了它们如何通过将原始高维优化问题分解为较小的子问题来提供有原则的数据驱动优化。这使我们能够为 DDO 推导出更实用的遗憾界,并且结果表明,在朴素方法因离线数据覆盖不足而失败的情况下,使用 FGMs 的 DDO 可以实现近乎最优的设计。我们进一步提出了一种数据驱动优化算法,该算法推断 FGM 结构本身,无论是在原始输入变量上还是在输入的潜变量表示上。

英文摘要:

While machine learning models are typically trained to solve prediction problems, we might often want to use them for optimization problems. For example, given a dataset of proteins and their corresponding fluorescence levels, we might want to optimize for a new protein with the highest possible fluorescence. This kind of data-driven optimization (DDO) presents a range of challenges beyond those in standard prediction problems, since we need models that successfully predict the performance of new designs that are better than the best designs seen in the training set. It is not clear theoretically when existing approaches can even perform better than the naive approach that simply selects the best design in the dataset. In this paper, we study how structure can enable sample-efficient data-driven optimization. To formalize the notion of structure, we introduce functional graphical models (FGMs) and show theoretically how they can provide for principled data-driven optimization by decomposing the original high-dimensional optimization problem into smaller sub-problems. This allows us to derive much more practical regret bounds for DDO, and the result implies that DDO with FGMs can achieve nearly optimal designs in situations where naive approaches fail due to insufficient coverage of the offline data. We further present a data-driven optimization algorithm that inferes the FGM structure itself, either over the original input variables or a latent variable representation of the inputs.

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。

↑