Results 1  10
of
179
How to Use Expert Advice
 JOURNAL OF THE ASSOCIATION FOR COMPUTING MACHINERY
, 1997
"... We analyze algorithms that predict a binary value by combining the predictions of several prediction strategies, called experts. Our analysis is for worstcase situations, i.e., we make no assumptions about the way the sequence of bits to be predicted is generated. We measure the performance of the ..."
Abstract

Cited by 369 (76 self)
 Add to MetaCart
We analyze algorithms that predict a binary value by combining the predictions of several prediction strategies, called experts. Our analysis is for worstcase situations, i.e., we make no assumptions about the way the sequence of bits to be predicted is generated. We measure the performance of the algorithm by the difference between the expected number of mistakes it makes on the bit sequence and the expected number of mistakes made by the best expert on this sequence, where the expectation is taken with respect to the randomization in the predictions. We show that the minimum achievable difference is on the order of the square root of the number of mistakes of the best expert, and we give efficient algorithms that achieve this. Our upper and lower bounds have matching leading constants in most cases. We then show howthis leads to certain kinds of pattern recognition/learning algorithms with performance bounds that improve on the best results currently known in this context. We also compare our analysis to the case in which log loss is used instead of the expected number of mistakes.
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 164 (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
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 161 (21 self)
 Add to MetaCart
(Show Context)
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.
Lectures on the central limit theorem for empirical processes
 Probability and Banach Spaces
, 1986
"... Abstract. Concentration inequalities are used to derive some new inequalities for ratiotype suprema of empirical processes. These general inequalities are used to prove several new limit theorems for ratiotype suprema and to recover anumber of the results from [1] and [2]. As a statistical applica ..."
Abstract

Cited by 135 (9 self)
 Add to MetaCart
(Show Context)
Abstract. Concentration inequalities are used to derive some new inequalities for ratiotype suprema of empirical processes. These general inequalities are used to prove several new limit theorems for ratiotype suprema and to recover anumber of the results from [1] and [2]. As a statistical application, an oracle inequality for nonparametric regression is obtained via ratio bounds. 1.
On Talagrand's Deviation Inequalities For Product Measures
, 1996
"... We present a new and simple approach to some of the deviation inequalities for product measures deeply investigated by M. ..."
Abstract

Cited by 112 (0 self)
 Add to MetaCart
We present a new and simple approach to some of the deviation inequalities for product measures deeply investigated by M.
A new look at independence
"... The concentration of measure phenomenon in product spaces is a farreaching abstract generalization of the classical exponential inequalities for sums of independent random variables. We attempt to explain in the simplest possible terms the basic concepts underlying this phenomenon, the basic method ..."
Abstract

Cited by 111 (0 self)
 Add to MetaCart
The concentration of measure phenomenon in product spaces is a farreaching abstract generalization of the classical exponential inequalities for sums of independent random variables. We attempt to explain in the simplest possible terms the basic concepts underlying this phenomenon, the basic method to prove concentration inequalities, and the meaning of several of the most useful inequalities.
Theory of classification: A survey of some recent advances
, 2005
"... The last few years have witnessed important new developments in the theory and practice of pattern classification. We intend to survey some of the main new ideas that have led to these recent results. ..."
Abstract

Cited by 91 (3 self)
 Add to MetaCart
The last few years have witnessed important new developments in the theory and practice of pattern classification. We intend to survey some of the main new ideas that have led to these recent results.
Theory and Applications of Agnostic PACLearning with Small Decision Trees
, 1995
"... We exhibit a theoretically founded algorithm T2 for agnostic PAClearning of decision trees of at most 2 levels, whose computation time is almost linear in the size of the training set. We evaluate the performance of this learning algorithm T2 on 15 common "realworld" datasets, and show t ..."
Abstract

Cited by 81 (3 self)
 Add to MetaCart
We exhibit a theoretically founded algorithm T2 for agnostic PAClearning of decision trees of at most 2 levels, whose computation time is almost linear in the size of the training set. We evaluate the performance of this learning algorithm T2 on 15 common "realworld" datasets, and show that for most of these datasets T2 provides simple decision trees with little or no loss in predictive power (compared with C4.5). In fact, for datasets with continuous attributes its error rate tends to be lower than that of C4.5. To the best of our knowledge this is the first time that a PAClearning algorithm is shown to be applicable to "realworld" classification problems. Since one can prove that T2 is an agnostic PAClearning algorithm, T2 is guaranteed to produce close to optimal 2level decision trees from sufficiently large training sets for any (!) distribution of data. In this regard T2 differs strongly from all other learning algorithms that are considered in applied machine learning, for w...
A few notes on statistical learning theory
 In S. Mendelson & A. Smola (Eds. ), Lecture Notes in Computer Science
, 2003
"... ..."
Fast rates for support vector machines using gaussian kernels
 Ann. Statist
, 2004
"... We establish learning rates up to the order of n −1 for support vector machines with hinge loss (L1SVMs) and nontrivial distributions. For the stochastic analysis of these algorithms we use recently developed concepts such as Tsybakov’s noise assumption and local Rademacher averages. Furthermore we ..."
Abstract

Cited by 68 (9 self)
 Add to MetaCart
(Show Context)
We establish learning rates up to the order of n −1 for support vector machines with hinge loss (L1SVMs) and nontrivial distributions. For the stochastic analysis of these algorithms we use recently developed concepts such as Tsybakov’s noise assumption and local Rademacher averages. Furthermore we introduce a new geometric noise condition for distributions that is used to bound the approximation error of Gaussian kernels in terms of their widths. 1