arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.11473stat.MLcs.LGcs.NEmath.STstat.APstat.TH
收藏

回归的迁移高斯过程

Transport Gaussian Processes for Regression

University of Chile(智利大学)

Gonzalo Rios

摘要:

高斯过程(GP)先验是非参数生成模型,具有贝叶斯推断的吸引人的建模特性:它们可以通过噪声观测来建模非线性关系,具有用于训练和推理的封闭形式表达式,并且由可解释的超参数控制。然而,GP模型依赖于高斯性,这是一个在几个现实世界场景中不成立的假设,例如,当观测值有界或具有极值依赖性时,这是物理学,金融和社会科学中的自然现象。虽然超高斯随机过程已经引起了GP社区的注意,但仍然缺乏原则性的定义和严格的处理。在这方面,我们提出了一种方法来构建随机过程,其中包括GP,翘曲GP,学生t过程和其他几个在一个统一的方法。我们还提供了在回归问题中训练和推断所提出的模型的公式和算法。我们的方法受到基于层的模型的启发,其中每个提议的层在生成的随机过程上改变特定的属性。反过来,这使我们能够将标准高斯白噪声推向其他更具表现力的随机过程,对于这些随机过程,边缘和Copula不需要是高斯的,同时保留GP的吸引人的属性。我们通过实验验证了所提出的模型与现实世界的数据。

英文摘要:

Gaussian process (GP) priors are non-parametric generative models with appealing modelling properties for Bayesian inference: they can model non-linear relationships through noisy observations, have closed-form expressions for training and inference, and are governed by interpretable hyperparameters. However, GP models rely on Gaussianity, an assumption that does not hold in several real-world scenarios, e.g., when observations are bounded or have extreme-value dependencies, a natural phenomenon in physics, finance and social sciences. Although beyond-Gaussian stochastic processes have caught the attention of the GP community, a principled definition and rigorous treatment is still lacking. In this regard, we propose a methodology to construct stochastic processes, which include GPs, warped GPs, Student-t processes and several others under a single unified approach. We also provide formulas and algorithms for training and inference of the proposed models in the regression problem. Our approach is inspired by layers-based models, where each proposed layer changes a specific property over the generated stochastic process. That, in turn, allows us to push-forward a standard Gaussian white noise prior towards other more expressive stochastic processes, for which marginals and copulas need not be Gaussian, while retaining the appealing properties of GPs. We validate the proposed model through experiments with real-world data.

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。

↑