Robust Multi-Hypothesis Testing with Moment Constrained Uncertainty Sets
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910288038592512 |
|---|---|
| author | Magesh, Akshayaa Sun, Zhongchang Veeravalli, Venugopal V. Zou, Shaofeng |
| author_facet | Magesh, Akshayaa Sun, Zhongchang Veeravalli, Venugopal V. Zou, Shaofeng |
| contents | The problem of robust binary hypothesis testing is studied. Under both hypotheses, the data-generating distributions are assumed to belong to uncertainty sets constructed through moments; in particular, the sets contain distributions whose moments are centered around the empirical moments obtained from training samples. The goal is to design a test that performs well under all distributions in the uncertainty sets, i.e., minimize the worst-case error probability over the uncertainty sets. In the finite-alphabet case, the optimal test is obtained. In the infinite-alphabet case, a tractable approximation to the worst-case error is derived that converges to the optimal value using finite samples from the alphabet. A test is further constructed to generalize to the entire alphabet. An exponentially consistent test for testing batch samples is also proposed. Numerical results are provided to demonstrate the performance of the proposed robust tests. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_12869 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Robust Multi-Hypothesis Testing with Moment Constrained Uncertainty Sets Magesh, Akshayaa Sun, Zhongchang Veeravalli, Venugopal V. Zou, Shaofeng Statistics Theory Information Theory The problem of robust binary hypothesis testing is studied. Under both hypotheses, the data-generating distributions are assumed to belong to uncertainty sets constructed through moments; in particular, the sets contain distributions whose moments are centered around the empirical moments obtained from training samples. The goal is to design a test that performs well under all distributions in the uncertainty sets, i.e., minimize the worst-case error probability over the uncertainty sets. In the finite-alphabet case, the optimal test is obtained. In the infinite-alphabet case, a tractable approximation to the worst-case error is derived that converges to the optimal value using finite samples from the alphabet. A test is further constructed to generalize to the entire alphabet. An exponentially consistent test for testing batch samples is also proposed. Numerical results are provided to demonstrate the performance of the proposed robust tests. |
| title | Robust Multi-Hypothesis Testing with Moment Constrained Uncertainty Sets |
| topic | Statistics Theory Information Theory |
| url | https://arxiv.org/abs/2210.12869 |