标题： ELBO最大化在模型选择中的一致性 显示英文标题

标题： Consistency of ELBO maximization for model selection

摘要： 证据下界（ELBO）是一个在变分推断中起关键作用的量。 它也可以用作模型选择的标准。 然而，尽管在变分贝叶斯领域实践中非常流行，但从未有普遍的理论依据来支持基于ELBO的选择。 在本文中，我们表明ELBO最大化策略具有强大的理论保证，并且对模型设定错误具有鲁棒性，而大多数工作都依赖于一个模型被正确设定的假设。 我们通过在概率PCA中选择主成分数量的应用来说明我们的理论结果。 显示英文摘要

摘要： The Evidence Lower Bound (ELBO) is a quantity that plays a key role in variational inference. It can also be used as a criterion in model selection. However, though extremely popular in practice in the variational Bayes community, there has never been a general theoretic justification for selecting based on the ELBO. In this paper, we show that the ELBO maximization strategy has strong theoretical guarantees, and is robust to model misspecification while most works rely on the assumption that one model is correctly specified. We illustrate our theoretical results by an application to the selection of the number of principal components in probabilistic PCA.