Random DFA's can be approximately learned from sparse uniform examples

@inproceedings{Lang1992RandomDC,
  title={Random DFA's can be approximately learned from sparse uniform examples},
  author={Kevin J. Lang},
  booktitle={COLT '92},
  year={1992}
}
Approximate inference of finite state machines from sparse labeled examples has been proved NP-hard when an adversary chooses the target machine and the training set [Ang78, KV89, PW89]. We have, however, empirically found that DFA's are approximately learnable from sparse data when the target machine and training set are selected at random. 

Figures from this paper

Lower Bounds on Learning Random Structures with Statistical Queries
We show that random DNF formulas, random log-depth decision trees and random deterministic finite acceptors cannot be weakly learned with a polynomial number of statistical queries with respect to an
Faster Algorithms for Finding Minimal Consistent DFAs
TLDR
Exbar, a powerful new algorithm for the exact inference of minimal deterministic automata from given training data, achieves the highest performance ever on a set of graded benchmark problems that has been posted by Arlindo Oliveira.
Learning deterministic finite automata with a smart state labeling evolutionary algorithm
TLDR
A novel evolutionary method for learning DFA that evolves only the transition matrix and uses a simple deterministic procedure to optimally assign state labels is described, which consistently outperforms EDSM, as well as other significant methods submitted to two recent competitions.
Efficient Algorithms for the Inference of Minimum Size DFAs
TLDR
The performance of algorithms that use implicit enumeration of solutions and algorithms that perform explicit search but incorporate a set of techniques known as dependency directed backtracking to prune the search tree effectively are analyzed.
Learning DFA from Simple Examples
TLDR
It is shown that efficient PAC learning of DFA is possible if the class of distributions is restricted to simple distributions where a teacher might choose examples based on the knowledge of the target concept.
Learning Dfa from Simple Examples Learning Dfa from Simple Examples
TLDR
It is shown that eecient PAC learning of DFA is possible if the class of distributions is restricted to simple distributions where a teacher might choose examples based on the knowledge of the target concept.
Learning deterministic regular grammars from stochastic samples in polynomial time
TLDR
A class of algorithms which allow for the identification of the structure of the minimal stochastic automaton generating the language are proposed and it is shown that the time needed grows only linearly with the size of the sample set.
Eecient Search Techniques for the Inference of Minimum Sized Finite State Machines
We propose a new algorithm for the inference of minimum size nite state machines from training set data. Our approach is based on a well known search algorithm proposed by Bierman, but it
A new algorithm for the reduction of incompletely specified finite state machines
  • J. M. Pena, A. Oliveira
  • Computer Science
    1998 IEEE/ACM International Conference on Computer-Aided Design. Digest of Technical Papers (IEEE Cat. No.98CB36287)
  • 1998
TLDR
An algorithm for the problem of state reduction in incompletely specified finite state machines is proposed and it is proved that the algorithm is exact and results show that it is much more efficient than both the explicit and implicit approaches based on the enumeration of compatible sets.
Search Techniques for the Inference of Minimum SizedFinite State
We propose a new algorithm for the inference of minimum size nite state machines from training set data. Our approach is based on a well known search algorithm proposed by Bierman, but it
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 13 REFERENCES
Inference of Sequential Machines from Sample Computations
This correspondence presents and justifies an algorithm for finding a minimal, though not a smallest, finite sequential machine with a behavior comprising a given finite sample of input-output
Cryptographic Limitations on Learning Boolean Formulae and Finite Automata
  • M. Kearns, L. Valiant
  • Computer Science, Mathematics
    Machine Learning: From Theory to Applications
  • 1993
TLDR
It is proved that a polynomial-time learning algorithm for Boolean formulae, deterministic finite automata or constant-depth threshold circuits would have dramatic consequences for cryptography and number theory and is applied to obtain strong intractability results for approximating a generalization of graph coloring.
On the Complexity of Minimum Inference of Regular Sets
  • D. Angluin
  • Mathematics, Computer Science
    Inf. Control.
  • 1978
The minimum consistent DFA problem cannot be approximated within and polynomial
TLDR
It is shown that for any constant k, no polynomial time algorithm can be guaranteed to find a consistent DFA of size optk, where opt is the size of a smallest DFA consistent with the sample.
The minimum consistent DFA problem cannot be approximated within any polynomial
TLDR
It is shown that for any constant k, no polynomial-time algorithm can be guaranteed to find a consistent DFA of size opt/sup k/, where opt is the size of a smallest DFA consistent with the sample.
Random number generators: good ones are hard to find
Practical and theoretical issues are presented concerning the design, implementation, and use of a good, minimal standard random number generator that will port to virtually all systems.
Crytographic limitations on learning Boolean formulae and finite automata
TLDR
It is proved that for Boolean formulae, finite automata, and constant depth threshold circuits (simplified neural nets), this problem is computationally as difficult as the quadratic residue problem, inverting the RSA function and factoring Blum integers.
The Minimum DFA Consistency Problem
  • 1989
The Minimum DFA Consistency Problem Cannot be Approximated Within any Polynomial
  • 1989
Random Number Generators: Good Ones
  • 1988
...
1
2
...