2 papers
cs.IT2026
On the Estimation of Chernoff Information
Kadircan Aksoy, Peter Jung
Chernoff information is a fundamental divergence measure characterizing the optimal error exponent in Bayesian binary hypothesis testing, with applications in information fusion, t…
cs.LG2026
Implicit Hypothesis Testing and Divergence Preservation in Neural Network Representations
Kadircan Aksoy, Protim Bhattacharjee, Peter Jung
We study the training dynamics of neural classifiers through the lens of binary hypothesis testing. We re-formalize classification as a collection of binary tests between class-con…