Results 1  10
of
31
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 121 (14 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
Empirical margin distributions and bounding the generalization error of combined classifiers
 Ann. Statist
, 2002
"... Dedicated to A.V. Skorohod on his seventieth birthday We prove new probabilistic upper bounds on generalization error of complex classifiers that are combinations of simple classifiers. Such combinations could be implemented by neural networks or by voting methods of combining the classifiers, such ..."
Abstract

Cited by 112 (8 self)
 Add to MetaCart
Dedicated to A.V. Skorohod on his seventieth birthday We prove new probabilistic upper bounds on generalization error of complex classifiers that are combinations of simple classifiers. Such combinations could be implemented by neural networks or by voting methods of combining the classifiers, such as boosting and bagging. The bounds are in terms of the empirical distribution of the margin of the combined classifier. They are based on the methods of the theory of Gaussian and empirical processes (comparison inequalities, symmetrization method, concentration inequalities) and they improve previous results of Bartlett (1998) on bounding the generalization error of neural networks in terms of ℓ1norms of the weights of neurons and of Schapire, Freund, Bartlett and Lee (1998) on bounding the generalization error of boosting. We also obtain rates of convergence in Lévy distance of empirical margin distribution to the true margin distribution uniformly over the classes of classifiers and prove the optimality of these rates.
Local Rademacher complexities
 Annals of Statistics
, 2002
"... We propose new bounds on the error of learning algorithms in terms of a datadependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical version of Rademacher averages, in the sense that the Rademacher averages are computed from the data, on a ..."
Abstract

Cited by 105 (18 self)
 Add to MetaCart
We propose new bounds on the error of learning algorithms in terms of a datadependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical version of Rademacher averages, in the sense that the Rademacher averages are computed from the data, on a subset of functions with small empirical error. We present some applications to classification and prediction with convex function classes, and with kernel classes in particular.
A few notes on Statistical Learning Theory
, 2003
"... this article is on the theoretical side and not on the applicative one; hence, we shall not present examples which may be interesting from the practical point of view but have little theoretical significance. This survey is far from being complete and it focuses on problems the author finds interest ..."
Abstract

Cited by 52 (10 self)
 Add to MetaCart
this article is on the theoretical side and not on the applicative one; hence, we shall not present examples which may be interesting from the practical point of view but have little theoretical significance. This survey is far from being complete and it focuses on problems the author finds interesting (an opinion which is not necessarily shared by the majority of the learning community). Relevant books which present a more evenly balanced approach are, for example [1, 4, 35, 36] The starting point of our discussion is the formulation of the learning problem. Consider a class G, consisting of real valued functions defined on a space #, and assume that each g G maps # into [0, 1]. Let T be an unknown function, T : # [0, 1] and set to be an unknown probability measure on #
Moment Inequalities for Functions of Independent Random Variables
"... this paper is to provide such generalpurpose inequalities. Our approach is based on a generalization of Ledoux's entropy method (see [26, 28]). Ledoux's method relies on abstract functional inequalities known as logarithmic Sobolev inequalities and provide a powerful tool for deriving exponential i ..."
Abstract

Cited by 39 (9 self)
 Add to MetaCart
this paper is to provide such generalpurpose inequalities. Our approach is based on a generalization of Ledoux's entropy method (see [26, 28]). Ledoux's method relies on abstract functional inequalities known as logarithmic Sobolev inequalities and provide a powerful tool for deriving exponential inequalities for functions of independent random variables, see Boucheron, Massart, and AMS 1991 subject classifications. Primary 60E15, 60C05, 28A35; Secondary 05C80 Key words and phrases. Moment inequalities, Concentration inequalities; Empirical processes; Random graphs Supported by EU Working Group RANDAPX, binational PROCOPE Grant 05923XL The work of the third author was supported by the Spanish Ministry of Science and Technology and FEDER, grant BMF200303324 Lugosi [6, 7], Bousquet [8], Devroye [14], Massart [30, 31], Rio [36] for various applications. To derive moment inequalities for general functions of independent random variables, we elaborate on the pioneering work of Latala and Oleszkiewicz [25] and describe socalled #Sobolev inequalities which interpolate between Poincare's inequality and logarithmic Sobolev inequalities (see also Beckner [4] and Bobkov's arguments in [26])
Complexity regularization via localized random penalties
, 2004
"... In this article, model selection via penalized empirical loss minimization in nonparametric classification problems is studied. Datadependent penalties are constructed, which are based on estimates of the complexity of a small subclass of each model class, containing only those functions with small ..."
Abstract

Cited by 24 (3 self)
 Add to MetaCart
In this article, model selection via penalized empirical loss minimization in nonparametric classification problems is studied. Datadependent penalties are constructed, which are based on estimates of the complexity of a small subclass of each model class, containing only those functions with small empirical loss. The penalties are novel since those considered in the literature are typically based on the entire model class. Oracle inequalities using these penalties are established, and the advantage of the new penalties over those based on the complexity of the whole model class is demonstrated.
Domain Adaptation: Learning Bounds and Algorithms
"... This paper addresses the general problem of domain adaptation which arises in a variety of applications where the distribution of the labeled sample available somewhat differs from that of the test data. Building on previous work by BenDavid et al. (2007), we introduce a novel distance between dist ..."
Abstract

Cited by 22 (4 self)
 Add to MetaCart
This paper addresses the general problem of domain adaptation which arises in a variety of applications where the distribution of the labeled sample available somewhat differs from that of the test data. Building on previous work by BenDavid et al. (2007), we introduce a novel distance between distributions, discrepancy distance, that is tailored to adaptation problems with arbitrary loss functions. We give Rademacher complexity bounds for estimating the discrepancy distance from finite samples for different loss functions. Using this distance, we derive new generalization bounds for domain adaptation for a wide family of loss functions. We also present a series of novel adaptation bounds for large classes of regularizationbased algorithms, including support vector machines and kernel ridge regression based on the empirical discrepancy. This motivates our analysis of the problem of minimizing the empirical discrepancy for various loss functions for which we also give several algorithms. We report the results of preliminary experiments that demonstrate the benefits of our discrepancy minimization algorithms for domain adaptation. 1
Empirical minimization
 Probability Theory and Related Fields, 135(3):311 – 334
, 2003
"... We investigate the behavior of the empirical minimization algorithm using various methods. We first analyze it by comparing the empirical, random, structure and the original one on the class, either in an additive sense, via the uniform law of large numbers, or in a multiplicative sense, using isomo ..."
Abstract

Cited by 19 (7 self)
 Add to MetaCart
We investigate the behavior of the empirical minimization algorithm using various methods. We first analyze it by comparing the empirical, random, structure and the original one on the class, either in an additive sense, via the uniform law of large numbers, or in a multiplicative sense, using isomorphic coordinate projections. We then show that a direct analysis of the empirical minimization algorithm yields a significantly better bound, and that the estimates we obtain are essentially sharp. The method of proof we use is based on Talagrand’s concentration inequality for empirical processes.
Concentration inequalities and asymptotic results for ratio type empirical processes
 Ann. Probab
, 2006
"... Let F be a class of measurable functions on a measurable space (S, S) with values in [0, 1] and let Pn = n −1 n ∑ δXi i=1 be the empirical measure based on an i.i.d. sample (X1,...,Xn) from a probability distribution P on (S, S). We study the behavior of suprema of the following type: sup rn<σP f ≤δ ..."
Abstract

Cited by 16 (4 self)
 Add to MetaCart
Let F be a class of measurable functions on a measurable space (S, S) with values in [0, 1] and let Pn = n −1 n ∑ δXi i=1 be the empirical measure based on an i.i.d. sample (X1,...,Xn) from a probability distribution P on (S, S). We study the behavior of suprema of the following type: sup rn<σP f ≤δn Pnf − Pf  φ(σPf) where σP f ≥ Var 1/2 P f and φ is a continuous, strictly increasing function with φ(0) = 0. Using Talagrand’s concentration inequality for empirical processes, we establish concentration inequalities for such suprema and use them to derive several results about their asymptotic behavior, expressing the conditions in terms of expectations of localized suprema of empirical processes. We also prove new bounds for expected values of supnorms of empirical processes in terms of the largest σP f and the L2(P) norm of the envelope of the function class, which are especially suited for estimating localized suprema. With this technique, we extend to function classes most of the known results on ratio type suprema of empirical processes, including some of Alexander’s results for VC classes of sets. We also consider applications of these results to several important problems in nonparametric statistics and in learning theory (including general excess risk bounds in empirical risk minimization and their versions for L2regression and classification and ratio type bounds for margin distributions in classification). 1. Introduction. Let