We show that the dependence on μ is necessary for every algorithm whose structure resembles existing ones. As a technical tool, a new variant of Statistical ...

A Lower Bound for Learning Distributions. Generated by Probabilistic Automata. Borja Balle, Jorge Castro, and Ricard Gavald`a. Universitat Polit`ecnica de ...

Known algorithms for learning PDFA can only be shown to run in time polynomial in the so-called distinguishability µ of the target machine, ...

Checking two probabilistic automata for equivalence has been shown to be a key problem for efficiently establishing various behavioural and anonymity properties ...

Abstract. Known algorithms for learning PDFA can only be shown to run in time polynomial in the so-called distinguishability µ of the target.

Finally, we show a lower bound: every algorithm to learn PDFA using queries with a resonable tolerance needs a number of queries larger than (1/μ) c for every c ...

Our results include a lower bound: every algorithm to learn PDFA with queries using a reasonable tolerance must make Ω ( 1 / μ 1 − c ) queries for every c > 0 .

1. The document discusses a lower bound for learning distributions generated by probabilistic automata (PDFA). 2. It introduces a new type of query called L ...

Oct 20, 2011 · Gavald`a, A Lower Bound for Learning Distributions Generated by Proba- bilistic Automata, in: M. Hutter, F. Stephan, V. Vovk, T. Zeugmann ...

A Lower Bound for Learning Distributions Generated by Probabilistic Automata · Computer Science. International Conference on Algorithmic Learning… · 2010.