• Corpus ID: 119130728

Dependency-dependent Bounds for Sums of Dependent Random Variables

@article{Lampert2018DependencydependentBF,
  title={Dependency-dependent Bounds for Sums of Dependent Random Variables},
  author={Christoph H. Lampert and Liva Ralaivola and Alexander Zimin},
  journal={arXiv: Probability},
  year={2018}
}
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… 

Figures from this paper

McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds
  • Rui
  • Computer Science
  • 2019
TLDR
This work proves novel McDiarmid-type concentration inequalities for Lipschitz functions of graph-dependent random variables and demonstrates that for many types of dependent data, the forest complexity is small and thus implies good concentration.
McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds
TLDR
This work proves novel McDiarmid-type concentration inequalities for Lipschitz functions of graph-dependent random variables and demonstrates that for many types of dependent data, the forest complexity is small and thus implies good concentration.
A Programming Language for Data Privacy with Accuracy Estimations
TLDR
The distinguishing feature of DPella is a novel component that statically tracks the accuracy of different data analyses, and leverages taint analysis for automatically inferring statistical independence of the different noise quantities added for guaranteeing privacy.
Correlation Tensor Decomposition and Its Application in Spatial Imaging Data
Multi-dimensional tensor data has gained increasing attention in recent years, especially in biomedical imaging analyses. However, most existing tensor models are only based on the mean information...
Generalization bounds for learning under graph-dependence: A survey
TLDR
This survey considers learning settings in which examples are dependent and their dependence relation-ship can be characterised by a graph, which is then used to derive Rademacher and stability generalization bounds for learning from graph-dependent data.

References

SHOWING 1-10 OF 31 REFERENCES
Large deviations for sums of partly dependent random variables
TLDR
A method by Hoeffding is used and extended to obtain strong large deviation bounds for sums of dependent random variables with suitable dependency structure and applications are given to U-statistics, random strings and random graphs.
Concentration Inequalities for Dependent Random Variables via the Martingale Method
The martingale method is used to establish concentration inequalities for a class of dependent random sequences on a countable state space, with the constants in the inequalities expressed in terms
Probability Inequalities for sums of Bounded Random Variables
Abstract Upper bounds are derived for the probability that the sum S of n independent random variables exceeds its mean ES by a positive number nt. It is assumed that the range of each summand of S
Concentration Inequalities - A Nonasymptotic Theory of Independence
TLDR
Deep connections with isoperimetric problems are revealed whilst special attention is paid to applications to the supremum of empirical processes.
Weighted dependency graphs
The theory of dependency graphs is a powerful toolbox to prove asymptotic normality of sums of random variables. In this article, we introduce a more general notion of weighted dependency graphs and
Chernoff-Hoeffding bounds for applications with limited independence
TLDR
The limited independence result implies that a reduced amount and weaker sources of randomness are sufficient for randomized algorithms whose analyses use the CH bounds, e.g., the analysis of randomized algorithms for random sampling and oblivious packet routing.
Auto-correlation Dependent Bounds for Relational Data
TLDR
This paper derives distribution free bounds for the relational setting where the class of data generation models it considers are inspired from the type joint distributions that are represented by relational classication models developed by the SRL community.
An Exponential Inequality for U-Statistics Under Mixing Conditions
  • Fang Han
  • Computer Science, Mathematics
  • 2016
TLDR
A novel exponential inequality for U-statistics under the time series setting is proved via exploiting the temporal correlatedness structure and applications to high-dimensional time series inference are discussed.
A Bernstein-type Inequality for Some Mixing Processes and Dynamical Systems with an Application to Learning
We establish a Bernstein-type inequality for a class of stochastic processes that include the classical geometrically $\phi$-mixing processes, Rio's generalization of these processes, as well as many
Constructive Proofs of Concentration Bounds
We give a combinatorial proof of the Chernoff-Hoeffding concentration bound [9,16], which says that the sum of independent {0, 1}- valued random variables is highly concentrated around the expected
...
1
2
3
4
...