Skip to Main content Skip to Navigation
Journal articles

Constructive Minimax Classification of Discrete Observations with Arbitrary Loss Function

Abstract : This paper develops a multihypothesis testing framework for calculating numerically the optimal minimax test with discrete observations and an arbitrary loss function. Discrete observations are common in data processing and make tractable the calculation of the minimax test. Each hypothesis is both associated to a parameter defining the distribution of the observations and to an action which describes the decision to take when the hypothesis is true. The loss function measures the gap between the parameters and the actions. The minimax test minimizes the maximum classification risk. It is the solution of a finite linear programming problem which gives the worst case classification risk and the worst case prior distribution. The minimax test equalizes the classification risks whose prior probabilities are strictly positive. The minimax framework is applied to vector channel decoding which consists in classifying some codewords transmitted on a binary asymmetric channel. The Hamming metric is used to measure the number of differences between the emitted codeword and the decoded one.
Complete list of metadatas

Cited literature [42 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01543555
Contributor : Lionel Fillatre <>
Submitted on : Wednesday, June 21, 2017 - 9:38:33 AM
Last modification on : Tuesday, May 26, 2020 - 6:50:53 PM
Document(s) archivé(s) le : Saturday, December 16, 2017 - 12:32:05 AM

File

fillatre_Constructive_Minimax_...
Files produced by the author(s)

Identifiers

Collections

Citation

Lionel Fillatre. Constructive Minimax Classification of Discrete Observations with Arbitrary Loss Function. Signal Processing, Elsevier, 2017, ⟨10.1016/j.sigpro.2017.06.020⟩. ⟨hal-01543555⟩

Share

Metrics