On learning bounded-width branching programs

In this paper, we study PAC-leaming algorithms for specialized classes of deterministic finite automata (DFA). Inpartictdar, we study branchingprogrsms, and we investigate the intluence of the width of the branching program on the difficulty of the learning problem. We first present a distribution-free algorithm for learning width-2 branching programs. We also give an algorithm for the proper learning of width-2 branching programs under uniform distribution on labeled samples. We then show that the existence of an efficient algorithm for learning width-3 branching programs would imply the existence of an efficient algorithm for learning DNF, which is not known to be the case. Fimlly, we show that the existence of an algorithm for learning width-3 branching programs would also yield an algorithm for learning a very restricted version of parity with noise.

[1]  Dana Ron,et al.  The Power of Amnesia , 1993, NIPS.

[2]  David A. Mix Barrington,et al.  Bounded-width polynomial-size branching programs recognize exactly those languages in NC1 , 1986, STOC '86.

[3]  E. Mark Gold,et al.  Complexity of Automaton Identification from Given Data , 1978, Inf. Control..

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

[5]  Leslie G. Valiant,et al.  Cryptographic Limitations on Learning Boolean Formulae and Finite Automata , 1993, Machine Learning: From Theory to Applications.

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

[7]  Manfred K. Warmuth,et al.  Learning integer lattices , 1990, COLT '90.

[8]  Dana Angluin,et al.  A Note on the Number of Queries Needed to Identify Regular Languages , 1981, Inf. Control..

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

[10]  Leonard Pitt,et al.  The minimum consistent DFA problem cannot be approximated within any polynomial , 1993, JACM.

[11]  K WarmuthManfred,et al.  The minimum consistent DFA problem cannot be approximated within any polynomial , 1993 .

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

[13]  Hinrich Schütze,et al.  Part-of-Speech Tagging Using a Variable Memory Markov Model , 1994, ACL.

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

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

[16]  V. Rich Personal communication , 1989, Nature.

[17]  Allan Borodin,et al.  Bounds for Width Two Branching Programs , 1986, SIAM J. Comput..

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

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

[20]  Allan Borodin,et al.  Bounds for width two branching programs , 1983, SIAM J. Comput..

[21]  Ronitt Rubinfeld,et al.  Efficient learning of typical finite automata from random walks , 1993, STOC.

[22]  Leslie G. Valiant,et al.  On the learnability of Boolean formulae , 1987, STOC.

[23]  Ronitt Rubinfeld,et al.  Learning fallible finite state automata , 1993, COLT '93.