Lange and Wiehagen's pattern language learning algorithm: An average-case analysis with respect to its total

• Authors: Thomas Zeugmann
• Venue: Annals of Mathematics and Artificial Intelligence
• Year: 1998

The present paper deals with the best‐case, worst‐case and average‐case behavior of Lange and Wiehagen’s (1991) pattern language learning algorithm with respect to its total learning time. Pattern languages have been introduced by Angluin (1980) and are defined as follows: Let \mathcal{A} = \{ 0,1,\dots\} be any non‐empty finite alphabet containing at least two elements. Furthermore, let X= \{x_i\mid i\in \mathbb{N}\} be an infinite set of variables such that \mathcal{A} \cap X = \emptyset. Patterns are non‐empty strings over \mathcal{A} \cup X. L(\pi), the language generated by pattern \pi, is the set of strings which can be obtained by substituting non‐null strings from \mathcal{A}^\ast for the variables of the pattern \pi. Lange and Wiehagen’s (1991) algorithm learns the class of all pattern languages in the limit from text. We analyze this algorithm with respect to its total learning time behavior, i.e., the overall time taken by the algorithm until convergence. For every pattern \pi containing k different variables it is shown that the total learning time is \mathrm{O}(\vert \pi\vert ^2 \log_{\vert \mathcal{A}\vert } (\vert \mathcal{A}\vert + k)) in the best‐case and unbounded in the worst‐case. Furthermore, we estimate the expectation of the total learning time. In particular, it is shown that Lange and Wiehagen’s algorithm possesses an expected total learning time of \mathrm{O}(2^kk^2\vert \pi\vert ^2\log_{\vert \mathcal{A}\vert }(k \vert \mathcal{A}\vert )) with respect to the uniform distribution.