Results 1  10
of
40
Random forests
 Machine Learning
, 2001
"... Abstract. Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the fo ..."
Abstract

Cited by 3613 (2 self)
 Add to MetaCart
Abstract. Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, ∗∗∗, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
Treebased batch mode reinforcement learning
 JOURNAL OF MACHINE LEARNING RESEARCH
, 2005
"... Reinforcement learning aims to determine an optimal control policy from interaction with a system or from observations gathered from a system. In batch mode, it can be achieved by approximating the socalled Qfunction based on a set of fourtuples (xt,ut,rt,xt+1) where xt denotes the system state a ..."
Abstract

Cited by 224 (42 self)
 Add to MetaCart
(Show Context)
Reinforcement learning aims to determine an optimal control policy from interaction with a system or from observations gathered from a system. In batch mode, it can be achieved by approximating the socalled Qfunction based on a set of fourtuples (xt,ut,rt,xt+1) where xt denotes the system state at time t, ut the control action taken, rt the instantaneous reward obtained and xt+1 the successor state of the system, and by determining the control policy from this Qfunction. The Qfunction approximation may be obtained from the limit of a sequence of (batch mode) supervised learning problems. Within this framework we describe the use of several classical treebased supervised learning methods (CART, Kdtree, tree bagging) and two newly proposed ensemble algorithms, namely extremely and totally randomized trees. We study their performances on several examples and find that the ensemble methods based on regression trees perform well in extracting relevant information about the optimal control policy from sets of fourtuples. In particular, the totally randomized trees give good results while ensuring the convergence of the sequence, whereas by relaxing the convergence constraint even better accuracy results are provided by the extremely randomized trees.
Boosting with the L_2Loss: Regression and Classification
, 2001
"... This paper investigates a variant of boosting, L 2 Boost, which is constructed from a functional gradient descent algorithm with the L 2 loss function. Based on an explicit stagewise re tting expression of L 2 Boost, the case of (symmetric) linear weak learners is studied in detail in both regressi ..."
Abstract

Cited by 208 (17 self)
 Add to MetaCart
This paper investigates a variant of boosting, L 2 Boost, which is constructed from a functional gradient descent algorithm with the L 2 loss function. Based on an explicit stagewise re tting expression of L 2 Boost, the case of (symmetric) linear weak learners is studied in detail in both regression and twoclass classification. In particular, with the boosting iteration m working as the smoothing or regularization parameter, a new exponential biasvariance trade off is found with the variance (complexity) term bounded as m tends to infinity. When the weak learner is a smoothing spline, an optimal rate of convergence result holds for both regression and twoclass classification. And this boosted smoothing spline adapts to higher order, unknown smoothness. Moreover, a simple expansion of the 01 loss function is derived to reveal the importance of the decision boundary, bias reduction, and impossibility of an additive biasvariance decomposition in classification. Finally, simulation and real data set results are obtained to demonstrate the attractiveness of L 2 Boost, particularly with a novel componentwise cubic smoothing spline as an effective and practical weak learner.
Convexity, Classification, and Risk Bounds
 JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
, 2003
"... Many of the classification algorithms developed in the machine learning literature, including the support vector machine and boosting, can be viewed as minimum contrast methods that minimize a convex surrogate of the 01 loss function. The convexity makes these algorithms computationally efficien ..."
Abstract

Cited by 181 (15 self)
 Add to MetaCart
Many of the classification algorithms developed in the machine learning literature, including the support vector machine and boosting, can be viewed as minimum contrast methods that minimize a convex surrogate of the 01 loss function. The convexity makes these algorithms computationally efficient. The use of a surrogate, however, has statistical consequences that must be balanced against the computational virtues of convexity. To study these issues, we provide a general quantitative relationship between the risk as assessed using the 01 loss and the risk as assessed using any nonnegative surrogate loss function. We show that this relationship gives nontrivial upper bounds on excess risk under the weakest possible condition on the loss function: that it satisfy a pointwise form of Fisher consistency for classification. The relationship is based on a simple variational transformation of the loss function that is easy to compute in many applications. We also present a refined version of this result in the case of low noise. Finally, we
Fast Binary Feature Selection with Conditional Mutual Information
 Journal of Machine Learning Research
, 2004
"... We propose in this paper a very fast feature selection technique based on conditional mutual information. ..."
Abstract

Cited by 176 (1 self)
 Add to MetaCart
(Show Context)
We propose in this paper a very fast feature selection technique based on conditional mutual information.
Statistical Behavior and Consistency of Classification Methods based on Convex Risk Minimization
, 2001
"... We study how close the optimal Bayes error rate can be approximately reached using a classification algorithm that computes a classifier by minimizing a convex upper bound of the classification error function. The measurement of closeness is characterized by the loss function used in the estimation. ..."
Abstract

Cited by 158 (6 self)
 Add to MetaCart
(Show Context)
We study how close the optimal Bayes error rate can be approximately reached using a classification algorithm that computes a classifier by minimizing a convex upper bound of the classification error function. The measurement of closeness is characterized by the loss function used in the estimation. We show that such a classification scheme can be generally regarded as a (non maximumlikelihood) conditional inclass probability estimate, and we use this analysis to compare various convex loss functions that have appeared in the literature. Furthermore, the theoretical insight allows us to design good loss functions with desirable properties. Another aspect of our analysis is to demonstrate the consistency of certain classification methods using convex risk minimization.
An introduction to boosting and leveraging
 Advanced Lectures on Machine Learning, LNCS
, 2003
"... ..."
(Show Context)
Boosting with early stopping: convergence and consistency
 Annals of Statistics
, 2003
"... Abstract Boosting is one of the most significant advances in machine learning for classification and regression. In its original and computationally flexible version, boosting seeks to minimize empirically a loss function in a greedy fashion. The resulted estimator takes an additive function form an ..."
Abstract

Cited by 66 (8 self)
 Add to MetaCart
Abstract Boosting is one of the most significant advances in machine learning for classification and regression. In its original and computationally flexible version, boosting seeks to minimize empirically a loss function in a greedy fashion. The resulted estimator takes an additive function form and is built iteratively by applying a base estimator (or learner) to updated samples depending on the previous iterations. An unusual regularization technique, early stopping, is employed based on CV or a test set. This paper studies numerical convergence, consistency, and statistical rates of convergence of boosting with early stopping, when it is carried out over the linear span of a family of basis functions. For general loss functions, we prove the convergence of boosting's greedy optimization to the infinimum of the loss function over the linear span. Using the numerical convergence result, we find early stopping strategies under which boosting is shown to be consistent based on iid samples, and we obtain bounds on the rates of convergence for boosting estimators. Simulation studies are also presented to illustrate the relevance of our theoretical results for providing insights to practical aspects of boosting. As a side product, these results also reveal the importance of restricting the greedy search step sizes, as known in practice through the works of Friedman and others. Moreover, our results lead to a rigorous proof that for a linearly separable problem, AdaBoost with ffl! 0 stepsize becomes an L1margin maximizer when left to run to convergence. 1 Introduction In this paper we consider boosting algorithms for classification and regression. These algorithms present one of the major progresses in machine learning. In their original version, the computational aspect is explicitly specified as part of the estimator/algorithm. That is, the empirical minimization of an appropriate loss function is carried out in a greedy fashion, which means that at each step, a basis function that leads to the largest reduction of empirical risk is added into the estimator. This specification distinguishes boosting from other statistical procedures which are defined by an empirical minimization of a loss function without the numerical optimization details.
Random Forests and Adaptive Nearest Neighbors
 JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
, 2002
"... ..."
Process Consistency for AdaBoost
 Annals of Statistics
, 2000
"... Introduction. Some recent experimental results [e.g., Friedman, Hastie and Tibshirani (1999); Grove and Schuurmans (1998); Mason et al. (1998)] and theoretical examples [Jiang (1999)] suggest that the AdaBoost algorithm [e.g., Schapire (1999); Freund and Schapire (1997)] can overfit in the limit of ..."
Abstract

Cited by 43 (1 self)
 Add to MetaCart
Introduction. Some recent experimental results [e.g., Friedman, Hastie and Tibshirani (1999); Grove and Schuurmans (1998); Mason et al. (1998)] and theoretical examples [Jiang (1999)] suggest that the AdaBoost algorithm [e.g., Schapire (1999); Freund and Schapire (1997)] can overfit in the limit of (very) large time (or the number of rounds of AdaBoost), despite the observation that the algorithm is often found to be resistant to overfitting after running hundreds of rounds. Jiang (1999) provides examples where it can be shown that the prediction error of Adaboost [P E(AdaBoost t n ), depending on the sample size n and the time t] is asymptotically suboptimal at t = 1, in the sense that the prediction at t = 1 is not consistent. Here by consistency of a prediction we mean that as the sample size n<F12.24