We propose a pixel-level out-of-distribution detection algorithm, called PixOOD, which does not require training on samples of anomalous data and is not designed for a specific application which avoids traditional tra...
详细信息
Recently, there has been a growing literature exploring the generalization of quantum algorithms, such that different quantum algorithms are special examples of a more fundamental structure. In this short paper, we pr...
详细信息
We develop an algorithm for jointly estimating the posterior and the noise parameters in Bayesian inverse problems, which is motivated by indirect measurements and applications from nanometrology with a mixed noise mo...
详细信息
Maximizing a target variable as an operational objective in a structural causal model is an important problem. Causal Bayesian Optimization (CBO) methods either rely on interventions that alter the causal structure to...
详细信息
Incremental expectationmaximization (EM) algorithms were introduced to design EM for the large scale learning framework by avoiding the full data set to be processed at each iteration. Nevertheless, these algorithms ...
详细信息
ISBN:
(纸本)9781728157672
Incremental expectationmaximization (EM) algorithms were introduced to design EM for the large scale learning framework by avoiding the full data set to be processed at each iteration. Nevertheless, these algorithms all assume that the conditional expectations of the sufficient statistics are explicit. In this paper, we propose a novel algorithm named Perturbed Prox-Preconditioned SPIDER (3P-SPIDER), which builds on the Stochastic Path Integral Differential EstimatoR EM (SPIDER-EM) algorithm. The 3P-SPIDER algorithm addresses many intractabilities of the E-step of EM;it also deals with non-smooth regularization and convex constraint set. Numerical experiments show that 3P-SPIDER outperforms other incremental EM methods and discuss the role of some design parameters.
Due to the complex structures and the multi-functionality of modern products, there are usually two or more performance characteristics which can reflect a product's degradation states. The degradation processes c...
详细信息
Due to the complex structures and the multi-functionality of modern products, there are usually two or more performance characteristics which can reflect a product's degradation states. The degradation processes corresponding to these performance characteristics are dependent in general, which brings challenges to the degradation data analysis. In this paper, a gamma process based degradation model is developed for the bivariate dependent degradation data, where the dependency between the two degradation processes is captured by a common random effect naturally. The expectation maximization algorithm is employed to estimate the model parameters. Then, a real-time prediction method for a product's remaining useful life is proposed using the Bayesian method. Finally, both the simulation study and the case study are provided for illustration, whose results demonstrate that the proposed model as well as the corresponding inference methods does work well.
We study multi-objective reinforcement learning with nonlinear preferences over trajectories. That is, we maximize the expected value of a nonlinear function over accumulated rewards (expected scalarized return or ESR...
详细信息
We propose a new class of models for variable clustering called Asymptotic Independent block (AI-block) models, which defines population-level clusters based on the independence of the maxima of a multivariate station...
详细信息
This paper introduces an innovative and intuitive finite population sampling method that have been developed using a unique geometric framework. In this approach, I represent first-order inclusion probabilities as bar...
详细信息
Dynamic factor models have been the main "big data'' tool used by empirical macroeconomists during the last 30 years. In this context, Kalman filter and smoothing (KFS) procedures can cope with missing da...
详细信息
Dynamic factor models have been the main "big data'' tool used by empirical macroeconomists during the last 30 years. In this context, Kalman filter and smoothing (KFS) procedures can cope with missing data, mixed frequency data, time-varying parameters, non-linearities, non-stationarity, and many other characteristics often observed in real systems of economic variables. The main contribution of this paper is to provide a comprehensive updated summary of the literature on latent common factors extracted using KFS procedures in the context of dynamic factor models, pointing out their potential limitations. Signal extraction and parameter estimation issues are separately analyzed. Identification issues are also tackled in both stationary and non-stationary models. Finally, empirical applications are surveyed in both cases. This survey is relevant to researchers and practitioners interested not only in the theory of KFS procedures for factor extraction in dynamic factor models but also in their empirical application in macroeconomics and finance. (C) 2021 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.
暂无评论