Further results on the margin explanation of boosting: new algorithm and experiments
نویسندگان
چکیده
منابع مشابه
On the Margin Explanation of Boosting Algorithms
Much attention has been paid to the theoretical explanation of the empirical success of AdaBoost. The most influential work is the margin theory, which is essentially an upper bound for the generalization error of any voting classifier in terms of the margin distribution over the training data. However, Breiman raised important questions about the margin explanation by developing a boosting alg...
متن کاملFurther Results on the Margin
A number of results have bounded generalization of a classiier in terms of its margin on the training points. There has been some debate about whether the minimum margin is the best measure of the distribution of training set margin values with which to estimate the generalization. Freund and Schapire 7] have shown how a diierent function of the margin distribution can be used to bound the numb...
متن کاملon the comparison of keyword and semantic-context methods of learning new vocabulary meaning
the rationale behind the present study is that particular learning strategies produce more effective results when applied together. the present study tried to investigate the efficiency of the semantic-context strategy alone with a technique called, keyword method. to clarify the point, the current study seeked to find answer to the following question: are the keyword and semantic-context metho...
15 صفحه اولOn the doubt about margin explanation of boosting
Margin theory provides one of the most popular explanations to the success of AdaBoost, where the central point lies in the recognition that margin is the key for characterizing the performance of AdaBoost. This theory has been very influential, e.g., it has been used to argue that AdaBoost usually does not overfit since it tends to enlarge the margin even after the training error reaches zero....
متن کاملExperiments with a New Boosting Algorithm
In an earlier paper, we introduced a new “boosting” algorithm called AdaBoost which, theoretically, can be used to significantly reduce the error of any learning algorithm that consistently generates classifiers whose performance is a little better than random guessing. We also introduced the related notion of a “pseudo-loss” which is a method for forcing a learning algorithm of multi-label con...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Science China Information Sciences
سال: 2012
ISSN: 1674-733X,1869-1919
DOI: 10.1007/s11432-012-4602-y