SaDe:可证明满足领域约束的学习模型
SaDe: Learning Models that Provably Satisfy Domain Constraints
摘要:
在机器学习的许多现实世界应用中,模型必须满足可以被表达为约束的某些基于域的要求(例如,自动驾驶系统中的安全关键约束)。在学习模型时,通常通过将这些约束包含在正则化项中来处理这些约束。然而,这种方法并不能保证100%满足约束:它只是减少了对训练集的约束的违反,而不是确保模型的预测总是遵守这些约束。在本文中,我们提出了一个学习模型的框架,可以证明在所有情况下都满足约束(即,也在看不见的数据上)。为了实现这一目标,我们将学习转换为最大可满足性问题,并使用一种新的SaDe算法解决它,该算法将约束满足与梯度下降相结合。我们将我们的方法与线性模型上基于正则化的基线进行了比较,并表明我们的方法能够有效地对看不见的数据实施不同类型的域约束,而不会牺牲预测性能。
英文摘要:
In many real world applications of machine learning, models have to meet certain domain-based requirements that can be expressed as constraints (e.g., safety-critical constraints in autonomous driving systems). Such constraints are often handled by including them in a regularization term, while learning a model. This approach, however, does not guarantee 100% satisfaction of the constraints: it only reduces violations of the constraints on the training set rather than ensuring that the predictions by the model will always adhere to them. In this paper, we present a framework for learning models that provably fulfil the constraints under all circumstances (i.e., also on unseen data). To achieve this, we cast learning as a maximum satisfiability problem, and solve it using a novel SaDe algorithm that combines constraint satisfaction with gradient descent. We compare our method against regularization based baselines on linear models and show that our method is capable of enforcing different types of domain constraints effectively on unseen data, without sacrificing predictive performance.
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。