|Strong Asymptotic Composition Theorems for Sibson Mutual Information
|Benjamin Huang Wu, Aaron B. Wagner, G. Edward Suh, Cornell University, United States; Ibrahim Issa, American University of Beirut, Lebanon
|S.9: Information Measures I
|Click here to download the manuscript
|Click here to watch in the Virtual Symposium
|We characterize the growth of the Sibson mutual information, of any order that is at least unity, between a random variable and an increasing set of noisy, conditionally independent observations of the random variable. The mutual information increases to an order-dependent limit exponentially fast, with an exponent that is order-independent. The result is constrasted with composition theorems in differential privacy.