arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1306.0040stat.COmath.STstat.MLstat.TH
收藏

逻辑斯谛回归的期望最大化

Expectation-maximization for logistic regression

James G. Scott, Liang Sun

摘要:

我们提出了一个家庭的期望最大化(EM)算法的二进制和负二项逻辑斯谛回归,绘制一个尖锐的连接与变分贝叶斯算法Jaakkola和约旦(2000年)。事实上,我们的研究结果允许这个版本的变分贝叶斯方法被重新解释为一个真正的期望最大化算法。我们研究了几个有趣的功能的算法,这以前未被识别的连接与变分贝叶斯。我们还推广的方法稀疏促进先验,并在线方法,其收敛性很容易建立。后一种方法在具有显著共线性的情况下与随机梯度下降法相比毫不逊色。

英文摘要:

We present a family of expectation-maximization (EM) algorithms for binary and negative-binomial logistic regression, drawing a sharp connection with the variational-Bayes algorithm of Jaakkola and Jordan (2000). Indeed, our results allow a version of this variational-Bayes approach to be re-interpreted as a true EM algorithm. We study several interesting features of the algorithm, and of this previously unrecognized connection with variational Bayes. We also generalize the approach to sparsity-promoting priors, and to an online method whose convergence properties are easily established. This latter method compares favorably with stochastic-gradient descent in situations with marked collinearity.

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。

↑