Related papers: Improved bounds for stochastic matching

This paper has been withdrawn at the author's request.

We present a new family of information-theoretic generalization bounds within the framework of conditional mutual information (CMI). Most of our results are established based on the leave-$m$-out (L$m$O) cross-validation error, with $m$…

In this version we have corrected some minor errors in the tables, corrected typos, and added a reference. We have also updated our comparison with earlier workers. Figures are now included as uuencoded compressed tar files.

The paper has been withdrawn by the author.

This paper has been withdrawn by the author(s), due to double submission. You can find it under: physics/0208019

This paper has been withdrawn by arXiv administrators because of an inappropriate amount of overlap with hep-th/0505013.

This paper has been withdrawn due to an error in one of the equations in the extended portion.

The author was informed that the result in the original version had been obtained earlier by K. Ueda (arXiv:math/0503355 [math.AG]). The paper is retracted.

We examine the relationship between the mutual information between the output model and the empirical sample and the generalization of the algorithm in the context of stochastic convex optimization. Despite increasing interest in…

This paper has been withdrawn by the author due to a coming paper completely superseding it.

We clarify a number of points raised in [Matias, arXiv:cond-mat/0507471v2 (2005)].

Merging asymptotic expansions of arbitrary length are established for the distribution functions and for the probabilities of suitably centered and normalized cumulative winnings in a full sequence of generalized St. Petersburg games,…

A technical flaw was found in this paper, and it has been withdrawn. It is intended that a modified version will be submitted soon.

This submission has been withdrawn by arXiv administrators because it is incomplete and thus violates arXiv policy.

In this appendix we provide additional supplementary material to "A Collective, Probabilistic Approach to Schema Mapping." We include an additional extended example, supplementary experiment details, and proof for the complexity result…

This paper has been withdrawn by the author. This draft is withdrawn for its poor quality in english, unfortunately produced by the author when he was just starting his science route. Look at the ICML version instead:…

This is a sequel to arXiv:1308.3604. We study applications to limit multiplicity generalizing the results of arXiv:1208.2257.

This paper has been withdrawn by the author, due to an error in relation (11).

In this paper, we derive new probability bounds for Chebyshev's inequality if the supremum of the probability density function is known. This result holds for one-dimensional or multivariate continuous probability distributions with finite…

This paper has been withdrawn by the author; a revised version is part of the author's phd-thesis "Quasi-logarithmic structures" (Zurich, 2007).