Learning models from observations of a system is a powerful tool with many applications. In this paper, we consider learning Discrete Time Markov Chains (DTMC), with different methods such as
frequency estimation
or
Laplace smoothing
. While models learnt with such methods converge asymptotically towards the exact system, a more practical question in the realm of trusted machine learning is how accurate a model learnt with a limited time budget is. Existing approaches provide bounds on how close the model is to the original system, in terms of bounds on
local
(transition) probabilities, which has unclear implication on the
global
behavior.
In this work, we provide
global bounds on the error
made by such a learning process, in terms of global behaviors formalized using
temporal logic
. More precisely, we propose a learning process ensuring a bound on the error in the probabilities of these properties. While such learning process cannot exist for the full LTL logic, we provide one ensuring a bound that is uniform over all the formulas of CTL. Further, given one time-to-failure property, we provide an improved learning algorithm. Interestingly, frequency estimation is sufficient for the latter, while Laplace smoothing is needed to ensure non-trivial uniform bounds for the full CTL logic.
Abstract-Diagnosability is the ability to detect a fault from partial observations collected on a system. It has been studied for numerous models of discrete event systems, but essentially from a logical perspective. This paper explores quantitative versions of the problem, to evaluate "how much" a system is (non-)diagnosable. For the diagnosable part of a system, that we characterize, we then examine the probability distribution of the detection delay. We show that the mean and the standard deviation of the detection delay can be easily evaluated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.