In this paper, we consider variational autoencoders (VAE) for general state space models. We consider a backward factorization of the variational distributions to analyze the excess risk associated with VAE. Such backward factorizations were recently proposed to perform online variational learning and to obtain upper bounds on the variational estimation error. When independent trajectories of sequences are observed and under strong mixing assumptions on the state space model and on the variational distribution, we provide an oracle inequality explicit in the number of samples and in the length of the observation sequences. We then derive consequences of this theoretical result. In particular, when the data distribution is given by a state space model, we provide an upper bound for the Kullback-Leibler divergence between the data distribution and its estimator and between the variational posterior and the estimated state space posterior distributions.Under classical assumptions, we prove that our results can be applied to Gaussian backward kernels built with dense and recurrent neural networks.
Learning with Semi-Definite Programming: new statistical bounds based on fixed point analysis and excess risk curvature
许多统计学习问题最近已经被证明是服从半定规划(SDP)的,其中高斯混合模型中的社区检测和聚类是最引人注目的实例[javanmard等人,2016年]。鉴于基于SDP的技术在机器学习问题中的应用范围越来越广,以及解决SDP的有效算法设计的快速进展,一个有趣的问题是理解如何将经验过程理论的最新进展投入工作,以提供SDP估计量的精确统计分析。在本文中,我们借用尖端技术和概念的学习理论文献,如不动点方程和超额风险曲率的参数,产生一般的估计和预测结果的广泛的SDP估计。从这个角度来看,我们回顾了社区检测中的一些经典结果[guédon et al.,2016]和[Chen等人,2016],并且我们获得了用于符号聚类,组同步和MAXCUT的SDP估计器的统计保证。
Excess risk of heat-related hospitalization associated with temperature and PM2.5 among older adults
Harvard T.H. Chan School of Public Health(哈佛陈曾熙公共卫生学院);Rutgers University Institute for Health, Healthcare Policy, and Aging Research(罗格斯大学健康、医疗政策与老龄化研究所);Rutgers University(罗格斯大学);Rutgers Robert Wood Johnson Medical School(罗格斯罗伯特·伍德·约翰逊医学院);Colorado School of Public Health(科罗拉多公共卫生学院)