Set systems: order types, continuous nondeterministic deformations, and quasi-orders
Yohji Akama

TL;DR
This paper explores the structure of set systems through order types, their relation to well-quasi-orders, and how continuous nondeterministic deformations preserve properties like finite elasticity, with implications for computational learning theory.
Contribution
It introduces a novel game-based definition of order types for set systems, links them to well-quasi-orders, and proves preservation of finite elasticity under continuous monotone functions.
Findings
Any well-quasi-order can be represented by a set system with matching maximal order type.
Finite elasticity is preserved under continuous, monotone functions and various language operators.
An order-type-preserving embedding exists from quasi-orders to subspaces of Cantor spaces.
Abstract
By reformulating a learning process of a set system L as a game between Teacher and Learner, we define the order type of L to be the order type of the game tree, if the tree is well-founded. The features of the order type of L (dim L in symbol) are (1) We can represent any well-quasi-order (wqo for short) by the set system L of the upper-closed sets of the wqo such that the maximal order type of the wqo is equal to dim L. (2) dim L is an upper bound of the mind-change complexity of L. dim L is defined iff L has a finite elasticity (fe for short), where, according to computational learning theory, if an indexed family of recursive languages has fe then it is learnable by an algorithm from positive data. Regarding set systems as subspaces of Cantor spaces, we prove that fe of set systems is preserved by any continuous function which is monotone with respect to the set-inclusion. By it, we…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputability, Logic, AI Algorithms · semigroups and automata theory · Machine Learning and Algorithms
