The inner-loop error-bound conjecture for unique information computation
Let and be the distributions produced by the inner-loop optimization, and let and be the corresponding expectation parameters for the marginal distributions on and . The quantities and measure the approximation errors in the distribution and expectation parameters, respectively.
Inner-loop error-bound conjecture.
This bound would provide the criterion needed to interrupt the inner iteration while guaranteeing a prescribed accuracy for the computed distribution. The supplied text does not indicate whether the claim has been proved or remains open.
References
- Pradeep Kr. Banerjee, Johannes Rauh and Guido Montúfar, “Computing the Unique Information”, arXiv:1709.07487 (2018).
Progress summary
Never refreshed
Nothing recorded yet. Refresh searches the literature and the public web for attempts on this problem, and writes the first summary here.
Solutions 0
No solutions have been posted yet.