Abstract
In computational function learning in the limit, an algorithmic learner tries to find a program for a computable function g given successively more values of g, each time outputting a conjectured program for g. A learner is called postdictively complete iff all available data is correctly postdicted by each conjecture.
Akama and Zeugmann presented, for each choice of natural number δ, a relaxation to postdictive completeness: each conjecture is required to postdict only all except the last δ seen data points.
This paper extends this notion of delayed postdictive completeness from constant delays to dynamically computed delays. On the one hand, the delays can be different for different data points. On the other hand, delays no longer need to be by a fixed finite number, but any type of computable countdown is allowed, including, for example, countdown in a system of ordinal notations and in other graphs disallowing computable infinitely descending counts.
We extend many of the theorems of Akama and Zeugmann and provide some feasible learnability results. Regarding fairness in feasible learning, one needs to limit use of tricks that postpone output hypotheses until there is enough time to “think” about them. We see, for polytime learning, postdictive completeness (and delayed variants): 1. allows some but not all postponement tricks, and 2. there is a surprisingly tight boundary, for polytime learning, between what postponement is allowed and what is not. For example: 1. the set of polytime computable functions is polytime postdictively completely learnable employing some postponement, but 2. the set of exptime computable functions, while polytime learnable with a little more postponement, is not polytime postdictively completely learnable! We have that, for w a notation for ω, the set of exptime functions is polytime learnable with w-delayed postdictive completeness. Also provided are generalizations to further, small constructive limit ordinals.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ambainis, A., Case, J., Jain, S., Suraj, M.: Parsimony hierarchies for inductive inference. Journal of Symbolic Logic 69, 287–328 (2004)
Akama, Y., Zeugmann, T.: Consistent and coherent learning with δ-delay. Technical Report TCS-TR-A-07-29, Hokkaido Univ. (October 2007)
Bārzdiņš, J.: Inductive inference of automata, functions and programs. In: Int. Math. Congress, Vancouver, pp. 771–776 (1974)
Blum, L., Blum, M.: Toward a mathematical theory of inductive inference. Information and Control 28, 125–155 (1975)
Case, J.: Periodicity in generations of automata. Mathematical Systems Theory 8, 15–32 (1974)
Case, J., Jain, S., Stephan, F., Wiehagen, R.: Robust learning – rich and poor. Journal of Computer and System Sciences 69, 123–165 (2004)
Case, J., Kötzing, T.: Dynamically delayed postdictive completeness and consistency in machine inductive inference (2008), http://www.cis.udel.edu/~case/papers/PcpPcsDelayTR.pdf
Case, J., Kötzing, T., Paddock, T.: Feasible iteration of feasible learning functionals. In: Hutter, M., Servedio, R.A., Takimoto, E. (eds.) ALT 2007. LNCS (LNAI), vol. 4754, pp. 34–48. Springer, Heidelberg (2007)
Freivalds, R., Smith, C.: On the role of procrastination in machine learning. Information and Computation 107(2), 237–271 (1993)
Fulk, M.: Saving the phenomena: Requirements that inductive machines not contradict known data. Inform. and Comp. 79, 193–209 (1988)
Jain, S., Osherson, D., Royer, J., Sharma, A.: Systems that Learn: An Introduction to Learning Theory, 2nd edn. MIT Press, Cambridge (1999)
Li, M., Vitanyi, P.: An Introduction to Kolmogorov Complexity and Its Applications, 2nd edn. Springer, Heidelberg (1997)
Minicozzi, E.: Some natural properties of strong identification in inductive inference. In: Theoretical Computer Science, pp. 345–360 (1976)
Pitt, L.: Inductive inference, DFAs, and computational complexity. In: Jantke, K.P. (ed.) AII 1989. LNCS, vol. 397, pp. 18–44. Springer, Heidelberg (1989)
Rogers, H.: Theory of Recursive Functions and Effective Computability. McGraw Hill, New York (1967) (Reprinted by MIT Press, Cambridge, Massachusetts, 1987)
Royer, J., Case, J.: Subrecursive Programming Systems. In: Progress in Theoretical Computer Science, Birkhäuser (1994)
Sharma, A., Stephan, F., Ventsov, Y.: Generalized notions of mind change complexity. Information and Computation 189, 235–262 (2004)
Wiehagen, R.: Limes-erkennung rekursiver Funktionen durch spezielle Strategien. Elek. Informationverarbeitung und Kyb. 12, 93–99 (1976)
Wiehagen, R.: Zur Theorie der Algorithmischen Erkennung. Dissertation B. Humboldt University of Berlin (1978)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Case, J., Kötzing, T. (2008). Dynamically Delayed Postdictive Completeness and Consistency in Learning. In: Freund, Y., Györfi, L., Turán, G., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2008. Lecture Notes in Computer Science(), vol 5254. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87987-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-540-87987-9_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87986-2
Online ISBN: 978-3-540-87987-9
eBook Packages: Computer ScienceComputer Science (R0)