Eecient Learning of Typical Finite Automata from Random Walks Extended Abstract

This paper describes new and e cient algorithms for learning deterministic nite automata. Our approach is primarily distinguished by two features: (1) the adoption of an average-case setting to model the \typical" labeling of a nite automaton, while retaining a worst-case model for the underlying graph of the automaton, along with (2) a learning model in which the learner is not provided with the means to experiment with the machine, but rather must learn solely by observing the automaton's output behavior on a random input sequence. The main contribution of this paper is in presenting the rst e cient algorithms for learning non-trivial classes of automata in an entirely passive learning model. We adopt an on-line learning model in which the learner is asked to predict the output of the next state, given the next symbol of the random input sequence; the goal of the learner is to make as few prediction mistakes as possible. Assuming the learner has a means of resetting the target machine to a xed start state, we rst present an e cient algorithm that makes an expected polynomial number of mistakes in this model. Next, we show how this rst algorithm can be used as a subroutine by a second algorithm that also makes a polynomial number of mistakes even in the absence of a reset. Along the way, we prove a number of combinatorial results for randomly labeled automata. We also show that the labeling of the states and the bits of the input sequence need not be truly random, but merely semi-random. Finally, we discuss an extension of our results to a model in which automata are used to represent distributions over binary strings.

[1]  Dana Ron,et al.  On the learnability and usage of acyclic probabilistic finite automata , 1995, COLT '95.

[2]  Ronitt Rubinfeld,et al.  On the learnability of discrete distributions , 1994, STOC '94.

[3]  Leslie G. Valiant,et al.  Cryptographic limitations on learning Boolean formulae and finite automata , 1994, JACM.

[4]  Kevin J. Lang Random DFA's can be approximately learned from sparse uniform examples , 1992, COLT '92.

[5]  Yossi Azar,et al.  Biased random walks , 1992, STOC '92.

[6]  N. Merhav,et al.  Universal prediction of individual sequences , 1991, 17th Convention of Electrical and Electronics Engineers in Israel.

[7]  Leonard Pitt,et al.  Prediction-Preserving Reducibility , 1990, J. Comput. Syst. Sci..

[8]  Avrim Blum Some tools for approximate 3-coloring , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

[9]  Leonard Pitt,et al.  The minimum consistent DFA problem cannot be approximated within any polynomial , 1989, [1989] Proceedings. Structure in Complexity Theory Fourth Annual Conference.

[10]  Ronald L. Rivest,et al.  Inference of finite automata using homing sequences , 1989, STOC '89.

[11]  Ronald L. Rivest,et al.  Learning complicated concepts reliably and usefully , 1988, Annual Conference Computational Learning Theory.

[12]  David Haussler,et al.  Predicting {0,1}-functions on randomly drawn points , 1988, COLT '88.

[13]  Leslie G. Valiant,et al.  Computational limitations on learning from examples , 1988, JACM.

[14]  Ronald L. Rivest,et al.  Diversity-based inference of finite automata , 1994, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[15]  Umesh V. Vazirani,et al.  Strong communication complexity or generating quasi-random sequences from two communicating semi-random sources , 1987, Comb..

[16]  Dana Angluin,et al.  Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..

[17]  Miklos Santha,et al.  Generating Quasi-random Sequences from Semi-random Sources , 1986, J. Comput. Syst. Sci..

[18]  Leslie Pack Kaelbling,et al.  Inferring finite automata with stochastic output functions and an application to map learning , 1992, 26th Annual Symposium on Foundations of Computer Science (sfcs 1985).

[19]  Vijay V. Vazirani,et al.  Random polynomial time is equal to slightly-random polynomial time , 1985, 26th Annual Symposium on Foundations of Computer Science (sfcs 1985).

[20]  Oded Goldreich,et al.  Unbiased bits from sources of weak randomness and probabilistic communication complexity , 1985, 26th Annual Symposium on Foundations of Computer Science (sfcs 1985).

[21]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[22]  DANA ANGLUIN,et al.  On the Complexity of Minimum Inference of Regular Sets , 1978, Inf. Control..

[23]  Boris A. Trakhtenbrot,et al.  Finite automata : behavior and synthesis , 1973 .

[24]  E. Mark Gold,et al.  System identification via state characterization , 1972 .