Dimension in Complexity Classes
نویسنده
چکیده
A theory of resource-bounded dimension is developed using gales, which are natural generalizations of martingales. When the resource bound ∆ (a parameter of the theory) is unrestricted, the resulting dimension is precisely the classical Hausdorff dimension (sometimes called “fractal dimension”). Other choices of the parameter ∆ yield internal dimension theories in E, E2, ESPACE, and other complexity classes, and in the class of all decidable problems. In general, if C is such a class, then every set X of languages has a dimension in C, which is a real number dim(X | C) ∈ [0, 1]. Along with the elements of this theory, two preliminary applications are presented: 1. For every real number 0 ≤ α ≤ 1 2 , the set FREQ(≤ α), consisting of all languages that asymptotically contain at most α of all strings, has dimension H(α) — the binary entropy of α — in E and in E2. 2. For every real number 0 ≤ α ≤ 1, the set SIZE(α n n ), consisting of all languages decidable by Boolean circuits of at most α n n gates, has dimension α in ESPACE.
منابع مشابه
Task Complexity Manipulation and Accuracy in Writing Performance
This study aimed to investigate the impact of task sequencing, along +/- reasoning demands dimension, on writing task performance in terms of accuracy. The study was motivated by Robinson’s Cognition Hypothesis (CH) as well as previous studies investigating the relationships between task complexity and second language production. The participants of the study were 90 intermediate students at t...
متن کاملThe Impact of Task Complexity along Single Task Dimension on EFL Iranian Learners' Written Production: Lexical complexity
Based on Robinson’s Cognition Hypothesis, this study explored the effects of task complexity on the lexical complexity of Iranian EFL students’ argumentative writing.This study was designed to explore the manipulation of cognitive task complexity along +/-single task dimension (a resource dispersing dimension in Robinson’s triadic framework) on Iranian EFL learners’ production in term of lexica...
متن کاملSauer's Bound for a Notion of Teaching Complexity
This paper establishes an upper bound on the size of a concept class with given recursive teaching dimension (RTD, a teaching complexity parameter.) The upper bound coincides with Sauer’s well-known bound on classes with a fixed VC-dimension. Our result thus supports the recently emerging conjecture that the combinatorics of VC-dimension and those of teaching complexity are intrinsically interl...
متن کاملRecursive Teaching Dimension, Learning Complexity, and Maximum Classes
This paper is concerned with the combinatorial structure of concept classes that can be learned from a small number of examples. We show that the recently introduced notion of recursive teaching dimension (RTD, reflecting the complexity of teaching a concept class) is a relevant parameter in this context. Comparing the RTD to self-directed learning, we establish new lower bounds on the query co...
متن کاملRecursive teaching dimension, VC-dimension and sample compression
This paper is concerned with various combinatorial parameters of classes that can be learned from a small set of examples. We show that the recursive teaching dimension, recently introduced by Zilles et al. (2008), is strongly connected to known complexity notions in machine learning, e.g., the self-directed learning complexity and the VC-dimension. To the best of our knowledge these are the fi...
متن کاملThe Effects of Task Complexity on English Language Learners’ Listening Comprehension
This article reports on the findings of a study that investigated the impact of manipulating task performance conditions on listening task performance by learners of English as a foreign language (EFL). The study was designed to explore the effects of changing complexity dimensions on listening task performance and to achieve two aims: to see how listening comprehension task performance was aff...
متن کامل