Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Dependency-dependent Bounds for Sums of Dependent Random Variables

Abstract : We consider the problem of bounding large deviations for non-i.i.d. random variables that are allowed to have arbitrary dependencies. Previous works typically assumed a specific dependence structure, namely the existence of independent components. Bounds that depend on the degree of dependence between the observations have only been studied in the theory of mixing processes, where variables are time-ordered. Here, we introduce a new way of measuring dependences within an unordered set of variables. We prove concentration inequalities, that apply to any set of random variables, but benefit from the presence of weak dependencies. We also discuss applications and extensions of our results to related problems of machine learning and large deviations.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02436776
Contributor : Liva Ralaivola <>
Submitted on : Monday, January 13, 2020 - 1:16:27 PM
Last modification on : Tuesday, March 3, 2020 - 1:23:05 AM

Links full text

Identifiers

  • HAL Id : hal-02436776, version 1
  • ARXIV : 1811.01404

Collections

Citation

Christoph H. Lampert, Liva Ralaivola, Alexander Zimin. Dependency-dependent Bounds for Sums of Dependent Random Variables. 2018. ⟨hal-02436776⟩

Share

Metrics

Record views

18