The Constructive Density-Ratio Approach to Mutual Information Estimation: An Experimental Comparison
نویسنده
چکیده
Mutual Information (MI) estimation is an important component of several data mining tasks (e.g feature selection). In classi cation settings, MI estimation essentially depends on the estimation of the ratio of two probability densities. Using a recently developed method of density-ratio estimation, which is constructive in nature, new estimators for MI can be derived. In this paper we consider one such new estimator VMI and compare it experimentally to previously proposed MI estimators. The experimental results show that VMI compare favorably to the other estimators.
منابع مشابه
Density Ratio Estimation: A New Versatile Tool for Machine Learning
A new general framework of statistical data processing based on the ratio of probability densities has been proposed recently and gathers a great deal of attention in the machine learning and data mining communities [1–17]. This density ratio framework includes various statistical data processing tasks such as non-stationarity adaptation [18, 1, 2, 4, 13], outlier detection [19–21, 6], and cond...
متن کاملMutual information for feature selection: estimation or counting?
In classification, feature selection is an important pre-processing step to simplify the dataset and improve the data representation quality, which makes classifiers become better, easier to train, and understand. Because of an ability to analyse non-linear interactions between features, mutual information has been widely applied to feature selection. Along with counting approaches, a tradition...
متن کاملThe Effectiveness of Imagotherapy on Process of Conversation and the Profound Relationship of Couples in Bandar Abbas city
This research was conducted with the aim of determining the effectiveness of imago therapy on the process of conversation and the profound relationship of couples in Bandar Abbas city. The design of the current research was semi-experimental with a pre-test-post-test design and a control group. The statistical population was all the couples from Bandar Abbas city who were referred to the counse...
متن کاملRigid point feature registration using mutual information
We have developed a new mutual information-based registration method for matching unlabeled point features. In contrast to earlier mutual information-based registration methods, which estimate the mutual information using image intensity information, our approach uses the point feature location information. A novel aspect of our approach is the emergence of correspondence (between the two sets ...
متن کاملApproximating Mutual Information by Maximum Likelihood Density Ratio Estimation
Mutual information is useful in various data processing tasks such as feature selection or independent component analysis. In this paper, we propose a new method of approximating mutual information based on maximum likelihood estimation of a density ratio function. Our method, called Maximum Likelihood Mutual Information (MLMI), has several attractive properties, e.g., density estimation is not...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013