A Note on Teaching for VC Classes

نویسندگان

  • Xi Chen
  • Yu Cheng
  • Bo Tang
چکیده

where we use c |X to denote the projection of c on X. The teaching dimension of C is the smallest number t such that every c ∈ C has a teaching set of size no more than t [GK95]. However, teaching dimension does not always capture the cooperation in teaching and learning, and the notion of recursive teaching dimension has been introduced and studied extensively in the literature [Kuh99, DSZ10, ZLHZ11, WY12, DFSZ14, SSYZ14, MSWY15]. The recursive teaching dimension of a class C ⊆ {0, 1}, denoted by RTD(C), is the smallest number t where one can order all the concepts of C as a sequence c1, . . . , c|C| such that every concept ci, i < |C|, has a teaching set of size no more than t in {ci, . . . , c|C|}. Hence, RTD(C) measures the worst-case number of labelled examples needed to learn any target concept in C, if the teacher and the learner agree a priori on a specific order of the concepts of the class C. In this note, we study the recursive teaching dimension of concept classes of low VC-dimension. Recall that the VC-dimension [VC71] of C ⊆ {0, 1}, denoted by VCD(C), is the maximum size of a shattered subset of [n], where Y ⊆ [n] is shattered if for every binary string b of length |Y |, there is a concept c ∈ C such that c |Y = b. Our main result is the following upper bound for RTD(C).

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Sauer'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 کامل

Recursive 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 کامل

Recursive 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 کامل

Teaching and compressing for low VC-dimension

In this work we study the quantitative relation between VC-dimension and two other basic parameters related to learning and teaching. We present relatively efficient constructions of sample compression schemes and teaching sets for classes of low VC-dimension. Let C be a finite boolean concept class of VC-dimension d. Set k = O(d2d log log |C|). We construct sample compression schemes of size k...

متن کامل

A note on bounds for VC dimensions.

We provide bounds for the VC dimension of class of sets formed by unions, intersections, and products of VC classes of sets 𝒞(1),…,𝒞(m.

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Electronic Colloquium on Computational Complexity (ECCC)

دوره 23  شماره 

صفحات  -

تاریخ انتشار 2016