Proceedings of the twenty-first international conference on Machine learning最新文献_第9页

Predictive automatic relevance determination by expectation propagation 基于期望传播的预测性自动相关性确定

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015418

Yuan Qi, T. Minka, Rosalind W. Picard, Zoubin Ghahramani

{"title":"Predictive automatic relevance determination by expectation propagation","authors":"Yuan Qi, T. Minka, Rosalind W. Picard, Zoubin Ghahramani","doi":"10.1145/1015330.1015418","DOIUrl":"https://doi.org/10.1145/1015330.1015418","url":null,"abstract":"In many real-world classification problems the input contains a large number of potentially irrelevant features. This paper proposes a new Bayesian framework for determining the relevance of input features. This approach extends one of the most successful Bayesian methods for feature selection and sparse learning, known as Automatic Relevance Determination (ARD). ARD finds the relevance of features by optimizing the model marginal likelihood, also known as the evidence. We show that this can lead to overfitting. To address this problem, we propose Predictive ARD based on estimating the predictive performance of the classifier. While the actual leave-one-out predictive performance is generally very costly to compute, the expectation propagation (EP) algorithm proposed by Minka provides an estimate of this predictive performance as a side-effect of its iterations. We exploit this in our algorithm to do feature selection, and to select data points in a sparse Bayesian kernel classifier. Moreover, we provide two other improvements to previous algorithms, by replacing Laplace's approximation with the generally more accurate EP, and by incorporating the fast optimization algorithm proposed by Faul and Tipping. Our experiments show that our method based on the EP estimate of predictive performance is more accurate on test data than relevance determination by optimizing the evidence.","PeriodicalId":159792,"journal":{"name":"Proceedings of the twenty-first international conference on Machine learning","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131772998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 123

A kernel view of the dimensionality reduction of manifolds 流形降维的核观点

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015417

Jihun Ham, Daniel D. Lee, S. Mika, B. Scholkopf

引用次数: 607

Generative modeling for continuous non-linearly embedded visual inference 连续非线性嵌入视觉推理的生成建模

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015371

C. Sminchisescu, A. Jepson

{"title":"Generative modeling for continuous non-linearly embedded visual inference","authors":"C. Sminchisescu, A. Jepson","doi":"10.1145/1015330.1015371","DOIUrl":"https://doi.org/10.1145/1015330.1015371","url":null,"abstract":"Many difficult visual perception problems, like 3D human motion estimation, can be formulated in terms of inference using complex generative models, defined over high-dimensional state spaces. Despite progress, optimizing such models is difficult because prior knowledge cannot be flexibly integrated in order to reshape an initially designed representation space. Nonlinearities, inherent sparsity of high-dimensional training sets, and lack of global continuity makes dimensionality reduction challenging and low-dimensional search inefficient. To address these problems, we present a learning and inference algorithm that restricts visual tracking to automatically extracted, non-linearly embedded, low-dimensional spaces. This formulation produces a layered generative model with reduced state representation, that can be estimated using efficient continuous optimization methods. Our prior flattening method allows a simple analytic treatment of low-dimensional intrinsic curvature constraints, and allows consistent interpolation operations. We analyze reduced manifolds for human interaction activities, and demonstrate that the algorithm learns continuous generative models that are useful for tracking and for the reconstruction of 3D human motion in monocular video.","PeriodicalId":159792,"journal":{"name":"Proceedings of the twenty-first international conference on Machine learning","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124543907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 172

Margin based feature selection - theory and algorithms 基于边际的特征选择理论与算法

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015352

Ran Gilad-Bachrach, A. Navot, Naftali Tishby

引用次数: 441

Nonparametric classification with polynomial MPMC cascades 多项式MPMC级联的非参数分类

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015416

S. Bohté, M. Breitenbach, G. Grudic

引用次数: 4

Links between perceptrons, MLPs and SVMs 感知机，mlp和svm之间的联系

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015415

Ronan Collobert, Samy Bengio

引用次数: 315

Redundant feature elimination for multi-class problems 多类问题的冗余特征消除

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015397

A. Appice, Michelangelo Ceci, S. Rawles, Peter A. Flach

引用次数: 56

Linearized cluster assignment via spectral ordering 通过谱排序线性化聚类分配

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015407

C. Ding, Xiaofeng He

{"title":"Linearized cluster assignment via spectral ordering","authors":"C. Ding, Xiaofeng He","doi":"10.1145/1015330.1015407","DOIUrl":"https://doi.org/10.1145/1015330.1015407","url":null,"abstract":"Spectral clustering uses eigenvectors of the Laplacian of the similarity matrix. They are most conveniently applied to 2-way clustering problems. When applying to multi-way clustering, either the 2-way spectral clustering is recursively applied or an embedding to spectral space is done and some other methods are used to cluster the points. Here we propose and study a K-way cluster assignment method. The method transforms the problem to find valleys and peaks of a 1-D quantity called cluster crossing, which measures the symmetric cluster overlap across a cut point along a linear ordering of the data points. The method can either determine K clusters in one shot or recursively split a current cluster into several smaller ones. We show that a linear ordering based on a distance sensitive objective has a continuous solution which is the eigenvector of the Laplacian, showing the close relationship between clustering and ordering. The method relies on the connectivity matrix constructed as the truncated spectral expansion of the similarity matrix, useful for revealing cluster structure. The method is applied to newsgroups to illustrate introduced concepts; experiments show it outperforms the recursive 2-way clustering and the standard K-means clustering.","PeriodicalId":159792,"journal":{"name":"Proceedings of the twenty-first international conference on Machine learning","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131668477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 88

Surrogate maximization/minimization algorithms for AdaBoost and the logistic regression model AdaBoost的代理最大化/最小化算法和逻辑回归模型

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015342

Zhihua Zhang, J. Kwok, D. Yeung

引用次数: 24

A Monte Carlo analysis of ensemble classification 集成分类的蒙特卡罗分析

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015386

Roberto Esposito, L. Saitta

引用次数: 10