arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.10282cs.LGcs.CL
收藏

分布鲁棒优化问题中第二参与者的建模

Modeling the Second Player in Distributionally Robust Optimization

Carnegie Mellon University(卡内基梅隆大学);Stanford University(斯坦福大学)

Paul Michel, Tatsunori Hashimoto, Graham Neubig

摘要:

分布式鲁棒优化(DRO)提供了一个用于训练机器学习模型的框架,这些模型能够在相关数据分布的集合(“不确定性集”)上表现良好。这是通过求解最小-最大博弈来完成的:模型经过训练,以最小化不确定性集中所有分布的最大预期损失。虽然精心设计的不确定性集是成功的DRO过程的关键,以前的工作已被限制到相对简单的替代品,保持最小-最大优化问题完全易于处理,如$f$ -发散球。在本文中,我们主张使用神经生成模型来表征最坏情况的分布,允许更灵活和特定于问题的不确定性集的选择。然而,虽然概念上简单,但这种方法提出了许多实施和优化挑战。为了规避这些问题,我们提出了一个放松的KL约束的内部最大化目标,使DRO问题更适合于基于梯度的优化大规模生成模型,并开发模型选择算法来指导超参数搜索。在玩具设置和现实的NLP任务中,我们发现所提出的方法产生的模型比可比基线更强大。

英文摘要:

Distributionally robust optimization (DRO) provides a framework for training machine learning models that are able to perform well on a collection of related data distributions (the "uncertainty set"). This is done by solving a min-max game: the model is trained to minimize its maximum expected loss among all distributions in the uncertainty set. While careful design of the uncertainty set is critical to the success of the DRO procedure, previous work has been limited to relatively simple alternatives that keep the min-max optimization problem exactly tractable, such as $f$-divergence balls. In this paper, we argue instead for the use of neural generative models to characterize the worst-case distribution, allowing for more flexible and problem-specific selection of the uncertainty set. However, while simple conceptually, this approach poses a number of implementation and optimization challenges. To circumvent these issues, we propose a relaxation of the KL-constrained inner maximization objective that makes the DRO problem more amenable to gradient-based optimization of large scale generative models, and develop model selection heuristics to guide hyper-parameter search. On both toy settings and realistic NLP tasks, we find that the proposed approach yields models that are more robust than comparable baselines.

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。

↑