BLR-D: Applying Bilinear Logistic Regression to Factored Diagnosis Problems
In this paper, the authors address a pattern of diagnosis problems in which each of J entities produces the same K features, yet they are only informed of overall faults from the ensemble. Furthermore, they suspect that only certain entities and certain features are leading to the problem. The task, then, is to reliably identify which entities and which features are at fault. Such problems are particularly prevalent in the world of computer systems, in which a datacenter with hundreds of machines, each with the same performance counters, occasionally produces overall faults. In this paper, they present a means of using a constrained form of bilinear logistic regression for diagnosis in such problems.