Conjecture on powers of the Jensen–Shannon divergence
Statement
Let and be probability distributions, and let denote their classical Jensen–Shannon divergence. For , consider the powered divergence .
Conjecture on powers of the Jensen–Shannon divergence. The quantity is not a metric for .
The result would complete the classification established in the paper: the powered Jensen–Shannon divergence is a metric for and is not a metric for . Counterexamples are given for some subintervals of , depending on , but the assertion for the full interval remains open.
Record
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.