most citedComplexities of convex combinations and bounding the generalization error in classification

52 citations · 54 across the 8 of their papers we have counts for

collaborators

8 papers

math.PR2004

Deviation inequality for monotonic Boolean functions with application to a number of k-cycles in a random graph

Dmitry Panchenko

Using Talagrand's concentration inequality on the discrete cube {0,1}^m we show that given a real-valued function Z(x)on {0,1}^m that satisfies certain monotonicity conditions one…

math.PR2004

Symmetrization approach to concentration inequalities for empirical processes

Dmitry Panchenko

We introduce a symmetrization technique that allows us to translate a problem of controlling the deviation of some functionals on a product space from their mean into a problem of…

math.PR2004

Empirical margin distributions and bounding the generalization error of combined classifiers

Vladimir Koltchinskii, Dmitry Panchenko

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…

math.PR2004

Some extensions of an inequality of Vapnik and Chervonenkis

Dmitry Panchenko

The inequality of Vapnik and Chervonenkis controls the expectation of the function by its sample average uniformly over a VC-major class of functions taking into account the size o…

math.PR2004

Some Local Measures of Complexity of Convex Hulls and Generalization Bounds

Olivier Bousquet, Vladimir Koltchinskii, Dmitry Panchenko

We investigate measures of complexity of function classes based on continuity moduli of Gaussian and Rademacher processes. For Gaussian processes, we obtain bounds on the continuit…

math.PR2004

Rademacher processes and bounding the risk of function learning

Vladimir Koltchinskii, Dmitry Panchenko

We construct data dependent bounds on the risk in function learning problems. The bounds are based on the local norms of the Rademacher process indexed by the underlying function c…