• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 287
  • 67
  • 48
  • 32
  • 28
  • 18
  • 14
  • 13
  • 12
  • 9
  • 3
  • 3
  • 3
  • 2
  • 2
  • Tagged with
  • 666
  • 666
  • 359
  • 359
  • 150
  • 147
  • 101
  • 72
  • 66
  • 66
  • 65
  • 63
  • 62
  • 60
  • 60
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
91

依序選擇四字串使第二字串或第四字串先出現的後選優勢探討 / On the first occurrence of four strings with teams

謝松樺, Hsieh, Sung Hua Unknown Date (has links)
本論文主要是在探討依序選擇四個字串之下,是否存在一策略使得第二或第四字串有較大的機會比第一或第三字串先出現,也就是所謂的後選優勢是否存在。 利用電腦計算,我們發現字串長度為4,5,6時後選優勢確實存在,而當字串長度大於等於或等於7時,我們則證明了若第一字串為(0,0,...,0),(0,0,...,0,1),(1,1,...,1)或(1,1,...,1,0)時,後選者優勢亦存在。 / In the thesis, we consider about the first occurrence of four strings decided sequentially with teams. Team 1 consists string 1 and string 3; team 2 consists string 2 and string 4. It is interested in whether or not team 2 whose strings are decided after first string and third string are given separately gets an advantage in appearing with larger probability.Namely, given any string 1, we want to find a string 2 such that any string 3 corresponds to at least one string (string 4) making a larger probability for team 2 in appearing earlier than team 1. Based on the result from computer calculation, team 2 advantage over team 1 when the string length is 4, 5, and 6. This thesis also shows that team 2 gets an advantage for cases where string 1 is (0,0,...,0), (0,0,...,0,1), (1,1,...,1), (1,1,...,1,0) ,when the string length is larger than 6.
92

Vienos Markovo grandinės stacionaraus skirstinio uodegos vertinimas / Estimating the tail of the stationary distribution of one markov chain

Skorniakova, Aušra 04 July 2014 (has links)
Šiame darbe nagrinėta tam tikra asimptotiškai homogeninė Markovo grandinė ir rasta jos stacionaraus skirstinio uodegos asimptotika. Nagrinėta grandinė negali būti ištirta šiuo metu žinomais metodais, todėl darbas turi praktinę reikšmę. Spręstas uždavinys aktualus sunkių uodegų analizėje. / In this work we have investigated some asymptotically homogeneous Markov chain and found asymptotics of the stationary distribution tail. To our best knowledge, considered chain cannot be investigated by means of existing methods, hence obtained results have practical value. Solved problem is relevant in heavy tail analysis.
93

Bayesian Inference in Large-scale Problems

Johndrow, James Edward January 2016 (has links)
<p>Many modern applications fall into the category of "large-scale" statistical problems, in which both the number of observations n and the number of features or parameters p may be large. Many existing methods focus on point estimation, despite the continued relevance of uncertainty quantification in the sciences, where the number of parameters to estimate often exceeds the sample size, despite huge increases in the value of n typically seen in many fields. Thus, the tendency in some areas of industry to dispense with traditional statistical analysis on the basis that "n=all" is of little relevance outside of certain narrow applications. The main result of the Big Data revolution in most fields has instead been to make computation much harder without reducing the importance of uncertainty quantification. Bayesian methods excel at uncertainty quantification, but often scale poorly relative to alternatives. This conflict between the statistical advantages of Bayesian procedures and their substantial computational disadvantages is perhaps the greatest challenge facing modern Bayesian statistics, and is the primary motivation for the work presented here. </p><p>Two general strategies for scaling Bayesian inference are considered. The first is the development of methods that lend themselves to faster computation, and the second is design and characterization of computational algorithms that scale better in n or p. In the first instance, the focus is on joint inference outside of the standard problem of multivariate continuous data that has been a major focus of previous theoretical work in this area. In the second area, we pursue strategies for improving the speed of Markov chain Monte Carlo algorithms, and characterizing their performance in large-scale settings. Throughout, the focus is on rigorous theoretical evaluation combined with empirical demonstrations of performance and concordance with the theory.</p><p>One topic we consider is modeling the joint distribution of multivariate categorical data, often summarized in a contingency table. Contingency table analysis routinely relies on log-linear models, with latent structure analysis providing a common alternative. Latent structure models lead to a reduced rank tensor factorization of the probability mass function for multivariate categorical data, while log-linear models achieve dimensionality reduction through sparsity. Little is known about the relationship between these notions of dimensionality reduction in the two paradigms. In Chapter 2, we derive several results relating the support of a log-linear model to nonnegative ranks of the associated probability tensor. Motivated by these findings, we propose a new collapsed Tucker class of tensor decompositions, which bridge existing PARAFAC and Tucker decompositions, providing a more flexible framework for parsimoniously characterizing multivariate categorical data. Taking a Bayesian approach to inference, we illustrate empirical advantages of the new decompositions.</p><p>Latent class models for the joint distribution of multivariate categorical, such as the PARAFAC decomposition, data play an important role in the analysis of population structure. In this context, the number of latent classes is interpreted as the number of genetically distinct subpopulations of an organism, an important factor in the analysis of evolutionary processes and conservation status. Existing methods focus on point estimates of the number of subpopulations, and lack robust uncertainty quantification. Moreover, whether the number of latent classes in these models is even an identified parameter is an open question. In Chapter 3, we show that when the model is properly specified, the correct number of subpopulations can be recovered almost surely. We then propose an alternative method for estimating the number of latent subpopulations that provides good quantification of uncertainty, and provide a simple procedure for verifying that the proposed method is consistent for the number of subpopulations. The performance of the model in estimating the number of subpopulations and other common population structure inference problems is assessed in simulations and a real data application.</p><p>In contingency table analysis, sparse data is frequently encountered for even modest numbers of variables, resulting in non-existence of maximum likelihood estimates. A common solution is to obtain regularized estimates of the parameters of a log-linear model. Bayesian methods provide a coherent approach to regularization, but are often computationally intensive. Conjugate priors ease computational demands, but the conjugate Diaconis--Ylvisaker priors for the parameters of log-linear models do not give rise to closed form credible regions, complicating posterior inference. In Chapter 4 we derive the optimal Gaussian approximation to the posterior for log-linear models with Diaconis--Ylvisaker priors, and provide convergence rate and finite-sample bounds for the Kullback-Leibler divergence between the exact posterior and the optimal Gaussian approximation. We demonstrate empirically in simulations and a real data application that the approximation is highly accurate, even in relatively small samples. The proposed approximation provides a computationally scalable and principled approach to regularized estimation and approximate Bayesian inference for log-linear models. </p><p>Another challenging and somewhat non-standard joint modeling problem is inference on tail dependence in stochastic processes. In applications where extreme dependence is of interest, data are almost always time-indexed. Existing methods for inference and modeling in this setting often cluster extreme events or choose window sizes with the goal of preserving temporal information. In Chapter 5, we propose an alternative paradigm for inference on tail dependence in stochastic processes with arbitrary temporal dependence structure in the extremes, based on the idea that the information on strength of tail dependence and the temporal structure in this dependence are both encoded in waiting times between exceedances of high thresholds. We construct a class of time-indexed stochastic processes with tail dependence obtained by endowing the support points in de Haan's spectral representation of max-stable processes with velocities and lifetimes. We extend Smith's model to these max-stable velocity processes and obtain the distribution of waiting times between extreme events at multiple locations. Motivated by this result, a new definition of tail dependence is proposed that is a function of the distribution of waiting times between threshold exceedances, and an inferential framework is constructed for estimating the strength of extremal dependence and quantifying uncertainty in this paradigm. The method is applied to climatological, financial, and electrophysiology data. </p><p>The remainder of this thesis focuses on posterior computation by Markov chain Monte Carlo. The Markov Chain Monte Carlo method is the dominant paradigm for posterior computation in Bayesian analysis. It has long been common to control computation time by making approximations to the Markov transition kernel. Comparatively little attention has been paid to convergence and estimation error in these approximating Markov Chains. In Chapter 6, we propose a framework for assessing when to use approximations in MCMC algorithms, and how much error in the transition kernel should be tolerated to obtain optimal estimation performance with respect to a specified loss function and computational budget. The results require only ergodicity of the exact kernel and control of the kernel approximation accuracy. The theoretical framework is applied to approximations based on random subsets of data, low-rank approximations of Gaussian processes, and a novel approximating Markov chain for discrete mixture models.</p><p>Data augmentation Gibbs samplers are arguably the most popular class of algorithm for approximately sampling from the posterior distribution for the parameters of generalized linear models. The truncated Normal and Polya-Gamma data augmentation samplers are standard examples for probit and logit links, respectively. Motivated by an important problem in quantitative advertising, in Chapter 7 we consider the application of these algorithms to modeling rare events. We show that when the sample size is large but the observed number of successes is small, these data augmentation samplers mix very slowly, with a spectral gap that converges to zero at a rate at least proportional to the reciprocal of the square root of the sample size up to a log factor. In simulation studies, moderate sample sizes result in high autocorrelations and small effective sample sizes. Similar empirical results are observed for related data augmentation samplers for multinomial logit and probit models. When applied to a real quantitative advertising dataset, the data augmentation samplers mix very poorly. Conversely, Hamiltonian Monte Carlo and a type of independence chain Metropolis algorithm show good mixing on the same dataset.</p> / Dissertation
94

Clustering of Driver Data based on Driving Patterns

Kabra, Amit January 2019 (has links)
Data analysis methods are important to analyze the ever-growing enormous quantity of the high dimensional data. Cluster analysis separates or partitions the data into disjoint groups such that data in the same group are similar while data between groups are dissimilar. The focus of this thesis study is to identify natural groups or clusters of drivers using the data which is based on driving style. In finding such a group of drivers, evaluation of the combinations of dimensionality reduction and clustering algorithms is done. The dimensionality reduction algorithms used in this thesis are Principal Component Analysis (PCA) and t-distributed stochastic neighbour embedding (t-SNE). The clustering algorithms such as K-means Clustering and Hierarchical Clustering are selected after performing Literature Review. In this thesis, the evaluation of PCA with K-means, PCA with Hierarchical Clustering, t-SNE with K-means and t-SNE with Hierarchical Clustering is done. The evaluation was done on the Volvo Cars’ drivers dataset based on their driving styles. The dataset is normalized first and Markov Chain of driving styles is calculated. This Markov Chain dataset is of very high dimensions and hence dimensionality reduction algorithms are applied to reduce the dimensions. The reduced dimensions dataset is used as an input to selected clustering algorithms. The combinations of algorithms are evaluated using performance metrics like Silhouette Coefficient, Calinski-Harabasz Index and DaviesBouldin Index. Based on experiment and analysis, the combination of t-SNE and K-means algorithms is found to be the best in comparison to other combinations of algorithms in terms of all performance metrics and is chosen to cluster the drivers based on their driving styles.
95

Practice-driven solutions for inventory management problems in data-scarce environments

Wang, Le 03 June 2019 (has links)
Many firms are challenged to make inventory decisions with limited data, and high customer service level requirements. This thesis focuses on heuristic solutions for inventory management problems in data-scarce environments, employing rigorous mathematical frameworks and taking advantage of the information that is available in practice but often ignored in literature. We define a class of inventory models and solutions with demonstrable value in helping firms solve these challenges.
96

Classificação e detecção de variações de comportamento: uma abordagem aplicada à identificação de perfis de usuários / Classification and behavior variation detection: an approach applied to identify user profile

Santos, Matheus Lorenzo dos 12 December 2008 (has links)
Estudos comportamentais têm sido conduzidos, há séculos, por cientistas e filósofos, abordando assuntos tais como trajetórias de estrelas e planetas, organizações da sociedade, evolução dos seres vivos, comportamento e linguagem humana. Com o advento da computação, grandes quantidades de informação tornaram-se disponíveis, as quais geram novos desafios a fim de explorar e compreender variações comportamentais de interação com esses sistemas. Motivado por esses desafios e pela disponibilidade de informações, esta dissertação de mestrado propõe uma metodologia com objetivo de classificar, detectar e identificar padrões de comportamento. A fim de validar essa metodologia, modelou-se conhecimentos embutidos em informações relativas a interações de usuários durante a grafia digital de assinaturas (tais informações foram obtidas de uma base de dados do campeonato SVC2004 -- First International Signature Verification Competition). Os modelos de conhecimento gerados foram, posteriormente, empregados em experimentos visando o reconhecimento de assinaturas. Resultados obtidos foram comparados a outras abordagens propostas na literatura / Throughout the centuries, behavioral studies have been conducted by scientists and philosophers, approaching subjects such as stars and planet trajectories, social organizations, living beings, human behavior and language. With the advent of computer science, large amounts of information have been made available, which brings out new challenges in the interactive behavior context. Such challenges have motivated this master thesis which proposes a methodology to classify, detect and identify behavioral patterns. A digital signature verification database, obtained from the First International Signature Verification Competition (SVC2004), was used to validate the proposed methodology. Knowledge models were obtained and, afterwards, employed in signature verification experiments. Results were compared to other approaches from the literature
97

Modelagem estocástica do labirinto em cruz elevado / Elevated Plus Maze: a Stochastic Modeling

Arantes, Rafael 27 September 2016 (has links)
O labirinto em cruz elevado é muito usado em estudos relacionados à ansiedade em ratos. As medidas tradicionalmente usadas são o número de entradas e o tempo passado nos braços abertos. Trabalhos recentes analisam a movimentação no interior dos braços, mas não propõem um índice que resuma as análises feitas. Esta tese sintetiza as informações de um destes trabalhos em índices. Um dos índices propostos usa os tempos médios de primeira visita a cada posição do labirinto e o outro se baseia na distribuição estacionária de probabilidade, o primeiro é capaz de diferenciar grupos de ratos submetidos a diferentes drogas ansiolíticas. Além disso, a tese propõe um modelo de processo Markoviano que incorpora informações desconsideradas no modelo anterior. A comparação entre os modelos revelou valores super ou subestimados no primeiro. Por fim, esta tese propõe um modelo de cadeias de Markov considerando como estados o seguinte conjunto de comportamentos: \"rearing\", \"stretching\", \"dipping\", \"freezing\" e \"grooming\". Tal abordagem inédita, apesar de simplificar exageradamente o modelo, foi capaz de reproduzir várias características conhecidas da exploração. / The elevated plus maze is widely used in studies related to anxiety in rats. The most widely used measures are the amount of entries and time spent on open arms. Recent studies analyze the movement inside the arms, but do not propose an index that summarizes the analyzes. This thesis summarizes by indices the information in one of these studies. An index uses the first visit average time to each position of the maze and another is based on the stationary probability distribution, the first one are able to differentiate groups of rats submitted to different anxiolytic drugs. These thesis also proposes a Markov process model that incorporates more information than the other model. The comparison between the models showed over- or underestimated values in the first. Finally, this thesis proposes a Markov chains model considering the following behaviors as states: rearing, stretching, dipping, freezing and grooming. This new approach, though oversimplify the model was able to reproduce several known features of exploitation.
98

A comparison of Bayesian model selection based on MCMC with an application to GARCH-type models

Miazhynskaia, Tatiana, Frühwirth-Schnatter, Sylvia, Dorffner, Georg January 2003 (has links) (PDF)
This paper presents a comprehensive review and comparison of five computational methods for Bayesian model selection, based on MCMC simulations from posterior model parameter distributions. We apply these methods to a well-known and important class of models in financial time series analysis, namely GARCH and GARCH-t models for conditional return distributions (assuming normal and t-distributions). We compare their performance vis--vis the more common maximum likelihood-based model selection on both simulated and real market data. All five MCMC methods proved feasible in both cases, although differing in their computational demands. Results on simulated data show that for large degrees of freedom (where the t-distribution becomes more similar to a normal one), Bayesian model selection results in better decisions in favour of the true model than maximum likelihood. Results on market data show the feasibility of all model selection methods, mainly because the distributions appear to be decisively non-Gaussian. / Series: Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"
99

Classificação e detecção de variações de comportamento: uma abordagem aplicada à identificação de perfis de usuários / Classification and behavior variation detection: an approach applied to identify user profile

Matheus Lorenzo dos Santos 12 December 2008 (has links)
Estudos comportamentais têm sido conduzidos, há séculos, por cientistas e filósofos, abordando assuntos tais como trajetórias de estrelas e planetas, organizações da sociedade, evolução dos seres vivos, comportamento e linguagem humana. Com o advento da computação, grandes quantidades de informação tornaram-se disponíveis, as quais geram novos desafios a fim de explorar e compreender variações comportamentais de interação com esses sistemas. Motivado por esses desafios e pela disponibilidade de informações, esta dissertação de mestrado propõe uma metodologia com objetivo de classificar, detectar e identificar padrões de comportamento. A fim de validar essa metodologia, modelou-se conhecimentos embutidos em informações relativas a interações de usuários durante a grafia digital de assinaturas (tais informações foram obtidas de uma base de dados do campeonato SVC2004 -- First International Signature Verification Competition). Os modelos de conhecimento gerados foram, posteriormente, empregados em experimentos visando o reconhecimento de assinaturas. Resultados obtidos foram comparados a outras abordagens propostas na literatura / Throughout the centuries, behavioral studies have been conducted by scientists and philosophers, approaching subjects such as stars and planet trajectories, social organizations, living beings, human behavior and language. With the advent of computer science, large amounts of information have been made available, which brings out new challenges in the interactive behavior context. Such challenges have motivated this master thesis which proposes a methodology to classify, detect and identify behavioral patterns. A digital signature verification database, obtained from the First International Signature Verification Competition (SVC2004), was used to validate the proposed methodology. Knowledge models were obtained and, afterwards, employed in signature verification experiments. Results were compared to other approaches from the literature
100

Optimal Bayesian estimators for latent variable cluster models

Rastelli, Riccardo, Friel, Nial 11 1900 (has links) (PDF)
In cluster analysis interest lies in probabilistically capturing partitions of individuals, items or observations into groups, such that those belonging to the same group share similar attributes or relational profiles. Bayesian posterior samples for the latent allocation variables can be effectively obtained in a wide range of clustering models, including finite mixtures, infinite mixtures, hidden Markov models and block models for networks. However, due to the categorical nature of the clustering variables and the lack of scalable algorithms, summary tools that can interpret such samples are not available. We adopt a Bayesian decision theoretical approach to define an optimality criterion for clusterings and propose a fast and context-independent greedy algorithm to find the best allocations. One important facet of our approach is that the optimal number of groups is automatically selected, thereby solving the clustering and the model-choice problems at the same time. We consider several loss functions to compare partitions and show that our approach can accommodate a wide range of cases. Finally, we illustrate our approach on both artificial and real datasets for three different clustering models: Gaussian mixtures, stochastic block models and latent block models for networks.

Page generated in 0.0465 seconds