首页    期刊浏览 2024年11月26日 星期二
登录注册

文章基本信息

  • 标题:Hrushovski’s Encoding and ω-Categorical CSP Monsters
  • 本地全文:下载
  • 作者:Pierre Gillibert ; Julius Jonu{ {s}}as ; Michael Kompatscher
  • 期刊名称:LIPIcs : Leibniz International Proceedings in Informatics
  • 电子版ISSN:1868-8969
  • 出版年度:2020
  • 卷号:168
  • 页码:131:1-131:17
  • DOI:10.4230/LIPIcs.ICALP.2020.131
  • 出版社:Schloss Dagstuhl -- Leibniz-Zentrum fuer Informatik
  • 摘要:We produce a class of ω-categorical structures with finite signature by applying a model-theoretic construction - a refinement of an encoding due to Hrushosvki - to ω-categorical structures in a possibly infinite signature. We show that the encoded structures retain desirable algebraic properties of the original structures, but that the constraint satisfaction problems (CSPs) associated with these structures can be badly behaved in terms of computational complexity. This method allows us to systematically generate ω-categorical templates whose CSPs are complete for a variety of complexity classes of arbitrarily high complexity, and ω-categorical templates that show that membership in any given complexity class cannot be expressed by a set of identities on the polymorphisms. It moreover enables us to prove that recent results about the relevance of topology on polymorphism clones of ω-categorical structures also apply for CSP templates, i.e., structures in a finite language. Finally, we obtain a concrete algebraic criterion which could constitute a description of the delineation between tractability and NP-hardness in the dichotomy conjecture for first-order reducts of finitely bounded homogeneous structures.
  • 关键词:Constraint satisfaction problem; complexity; polymorphism; pointwise convergence topology; height 1 identity; ω-categoricity; orbit growth
国家哲学社会科学文献中心版权所有