DeepAI AI Chat
Log In Sign Up

Non-Asymptotic Chernoff Lower Bound and Its Application to Community Detection in Stochastic Block Model

12/29/2018
by   Zhixin Zhou, et al.
0

Chernoff coefficient is an upper bound of Bayes error probability in classification problem. In this paper, we will develop sharp Chernoff type bound on Bayes error probability. The new bound is not only an upper bound but also a lower bound of Bayes error probability up to a constant in a non-asymptotic setting. Moreover, we will apply this result to community detection in stochastic block model. As a clustering problem, the optimal error rate of community detection can be characterized by our Chernoff type bound. This can be formalized by deriving a minimax error rate over certain class of parameter space, then achieving such error rate by a feasible algorithm employ multiple steps of EM type updates.

READ FULL TEXT
02/03/2018

On the Minimax Misclassification Ratio of Hypergraph Community Detection

Community detection in hypergraphs is explored. Under a generative hyper...
09/10/2017

Rates of Convergence of Spectral Methods for Graphon Estimation

This paper studies the problem of estimating the grahpon model - the und...
05/09/2018

Dispersion Bound for the Wyner-Ahlswede-Körner Network via Reverse Hypercontractivity on Types

Using the functional-entropic duality and the reverse hypercontractivity...
04/21/2019

Achieving the Bayes Error Rate in Synchronization and Block Models by SDP, Robustly

We study the statistical performance of semidefinite programming (SDP) r...
01/20/2014

Generalized Bhattacharyya and Chernoff upper bounds on Bayes error using quasi-arithmetic means

Bayesian classification labels observations based on given prior informa...
05/15/2011

Bounds on the Bayes Error Given Moments

We show how to compute lower bounds for the supremum Bayes error if the ...
04/09/2015

`local' vs. `global' parameters -- breaking the gaussian complexity barrier

We show that if F is a convex class of functions that is L-subgaussian, ...