DeepAI AI Chat
Log In Sign Up

Second-Order Asymptotics of Hoeffding-Like Hypothesis Tests

by   K. V. Harsha, et al.
IIT Kharagpur
Universidad Carlos III de Madrid

We consider a binary statistical hypothesis testing problem, where n independent and identically distributed random variables Z^n are either distributed according to the null hypothesis P or the alternate hypothesis Q, and only P is known. For this problem, a well-known test is the Hoeffding test, which accepts P if the Kullback-Leibler (KL) divergence between the empirical distribution of Z^n and P is below some threshold. In this paper, we consider Hoeffding-like tests, where the KL divergence is replaced by other divergences, and characterize, for a large class of divergences, the first and second-order terms of the type-II error for a fixed type-I error. Since the considered class includes the KL divergence, we obtain the second-order term of the Hoeffiding test as a special case.


page 1

page 2

page 3

page 4


Second-Order Asymptotics of Sequential Hypothesis Testing

We consider the classical sequential binary hypothesis testing problem i...

Sub-Gaussian Error Bounds for Hypothesis Testing

We interpret likelihood-based test functions from a geometric perspectiv...

Agnostic tests can control the type I and type II errors simultaneously

Despite its common practice, statistical hypothesis testing presents cha...

Asymptotics of Sequential Composite Hypothesis Testing under Probabilistic Constraints

We consider the sequential composite binary hypothesis testing problem i...

The All-or-Nothing Phenomenon in Sparse Linear Regression

We study the problem of recovering a hidden binary k-sparse p-dimensiona...

Distributed Source Simulation With No Communication

We consider the problem of distributed source simulation with no communi...

Learning Bregman Divergences

Metric learning is the problem of learning a task-specific distance func...