This project considers a simple binary hypothesis testing scenario where the resource-constrained transmitter performs scalar compression on data sampled from one of two distributions; the receiver performs a hypothesis test on multiple received samples to determine the correct source distribution.
To this end, the task-oriented compression problem is formulated as finding the optimal source coder that maximizes the asymptotic error performance of the hypothesis test on the server side under a rate constraint.

An analysis of how to design task-oriented compressors is provided, giving intuitions about how to extract the semantic information which is relevant to the hypothesis test.

follow this research