DeepAI AI Chat
Log In Sign Up

Statistical Classification via Robust Hypothesis Testing: Non-Asymptotic and Simple Bounds

by   Hüseyin Afşer, et al.

We consider Bayesian multiple statistical classification problem in the case where the unknown source distributions are estimated from the labeled training sequences, then the estimates are used as nominal distributions in a robust hypothesis test. Specifically, we employ the DGL test due to Devroye et al. and provide non-asymptotic, exponential upper bounds on the error probability of classification. The proposed upper bounds are simple to evaluate and reveal the effects of the length of the training sequences, the alphabet size and the numbers of hypothesis on the error exponent. The proposed method can also be used for large alphabet sources when the alphabet grows sub-quadratically in the length of the test sequence. The simulations indicate that the performance of the proposed method gets close to that of optimal hypothesis testing as the length of the training sequences increases.


page 1

page 2

page 3

page 4


Statistical Classification via Robust Hypothesis Testing

In this letter, we consider multiple statistical classification problem ...

Some Remarks on Bayesian Multiple Hypothesis Testing

We consider Bayesian multiple hypothesis problem with independent and id...

Achievable Error Exponents for Almost Fixed-Length Hypothesis Testing and Classification

We revisit multiple hypothesis testing and propose a two-phase test, whe...

Do Random and Chaotic Sequences Really Cause Different PSO Performance?

Our topic is performance differences between using random and chaos for ...

Evaluation of Error Probability of Classification Based on the Analysis of the Bayes Code

Suppose that we have two training sequences generated by parametrized di...

Testing for Anomalies: Active Strategies and Non-asymptotic Analysis

The problem of verifying whether a multi-component system has anomalies ...

Single-Shot Compression for Hypothesis Testing

Enhanced processing power in the cloud allows constrained devices to off...