$α$-Geodesical Skew Divergence
This is an incremental theoretical contribution for information geometry and divergence-based machine learning methods.
The authors proposed an information geometric generalization of the skew divergence called the α-geodesical skew divergence and studied its properties, addressing the limitation of requiring absolute continuity in KL divergence approximations.
The asymmetric skew divergence smooths one of the distributions by mixing it, to a degree determined by the parameter $λ$, with the other distribution. Such divergence is an approximation of the KL divergence that does not require the target distribution to be absolutely continuous with respect to the source distribution. In this paper, an information geometric generalization of the skew divergence called the $α$-geodesical skew divergence is proposed, and its properties are studied.