Margin-adaptive model selection in statistical learning
نویسندگان
چکیده
منابع مشابه
Margin-adaptive model selection in statistical learning
A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning framework. Actually, we consider a weaker version of this condition that allows one to take into account that learning within a small model can be much easier t...
متن کاملLarge Margin Subspace Learning for feature selection
Recent research has shown the benefits of large margin framework for feature selection. In this paper, we propose a novel feature selection algorithm, termed as Large Margin Subspace Learning (LMSL), which seeks a projection matrix to maximize the margin of a given sample, defined as the distance between the nearest missing (the nearest neighbor with the different label) and the nearest hit (th...
متن کاملLearning lexicons from spoken utterances based on statistical model selection
This paper proposes a method for the unsupervised learning of lexicons from pairs of a spoken utterance and an object as its meaning without any a priori linguistic knowledge other than a phoneme acoustic model. In order to obtain a lexicon, a statistical model of the joint probability of a spoken utterance and an object is learned based on the minimum description length principle. This model c...
متن کاملModel Selection and Automatic Model Selection for Statistical Learning: A Comparative Study on Local Factor Analysis
Given a paremetric model, the task of statistical learning consists of a parameter learning part for determining unknown parameters and a model selection part for selecting an appropriate scale for a model that accommodates these parameters. Typically, the two tasks are implemented in a twophase procedure. First, a number of models of a same architecture but in different scales are enumerated, ...
متن کاملSelection of Learning Methods Using an Adaptive Model ofKnowledge
Experiments measuring knowledge utility during the course of learning reveal a common behavior among several learning methods. As the amount of learned knowledge increases, the utility (performance) of the knowledge initially increases, but eventually degrades. A multistrategy learning system based on a model of this common behavior selects a learning method according to the model's prediction ...
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: Bernoulli
سال: 2011
ISSN: 1350-7265
DOI: 10.3150/10-bej288