A Sufficient Condition for Polynomial Distribution-dependent Learnability
نویسندگان
چکیده
We investigate upper bounds on the sample-size sufficient for ‘solid’ learnability with respect to a probability distribution. We obtain a sufficient condition for feasible (polynomially bounded) sample-size bounds for distributionspecific (solid) learnability.
منابع مشابه
Learning with prior information
In this paper, a new notion of learnability is introduced, referred to as learnability with prior information (w.p.i.). This notion is weaker than the standard notion of probably approximately correct (PAC) learnability which has been much studied during recent years. A property called “dispersability” is introduced, and it is shown that dispersability plays a key role in the study of learnabil...
متن کاملOccam Algorithms for Learning From Noisy Examples
In the distribution-independent model of concept learning from examples introduced by Valiant [Va184], it has been shown that the existence of an Occam algorithm for a dass of concepts implies the computationally feasible (polynomial) learnability of that class $[BEHW87a, BEHW87b]$. An Occam algorithm is a polynomial-time algorithm that produces, for any sequence of examples, a nearly minimum h...
متن کاملThe Consistency Dimension and Distribution-dependent Learning from Queries (extended Abstract with Appendices)
We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnabil-ity via equivalence and membership queries of its subclasses obtained by restricting the instance space. Then we propose and study two models of query learning in which there is a probability distribution on...
متن کاملThe Consistency Dimension and Distribution-Dependent Learning from Queries (Extended Abstract)
We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence and membership queries of its subclasses obtained by restricting the instance space. Then we propose and study two models of query learning in which there is a probability distribution on ...
متن کاملUniform Convergence, Stability and Learnability for Ranking Problems
Most studies were devoted to the design of efficient algorithms and the evaluation and application on diverse ranking problems, whereas few work has been paid to the theoretical studies on ranking learnability. In this paper, we study the relation between uniform convergence, stability and learnability of ranking. In contrast to supervised learning where the learnability is equivalent to unifor...
متن کاملذخیره 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 ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Discrete Applied Mathematics
دوره 77 شماره
صفحات -
تاریخ انتشار 1997