PAC learning, VC dimension, and the arithmetic hierarchy
نویسنده
چکیده
We compute that the index set of PAC-learnable concept classes is m-complete Σ 3 within the set of indices for all concept classes of a reasonable form. All concept classes considered are computable enumerations of computable Π 1 classes, in a sense made precise here. This family of concept classes is sufficient to cover all standard examples, and also has the property that PAC learnability is equivalent to finite VC dimension.
منابع مشابه
Higher dimensional PAC - learning and VC - dimension
The VC-dimension (Vapnic-Chervonenkis dimension) was introduced in 1970’s related to computational learning theory, combinatorics, and model theory which is a branch of mathematical logic. In fact, it is well known that for given class C, PAC-learnability of C, the finiteness of VC-dimension of C, and the dependency (which is a notion in model theory) of a formula defines C are essentially the ...
متن کاملA generalization of the PAC learning in product probability spaces
Three notions dependent theory, VC-dimension, and PAC-learnability have been found to be closely related. In addition to the known relation among these notions in model theory, finite combinatorics and probability theory, Chernikov, Palacin, and Takeuchi found a relation between n-dependence and VCn-dimension, which are generalizations of dependence and VC-dimension respectively. We are now wor...
متن کاملError Bounds for Real Function Classes Based on Discretized Vapnik-Chervonenkis Dimensions
The Vapnik-Chervonenkis (VC) dimension plays an important role in statistical learning theory. In this paper, we propose the discretized VC dimension obtained by discretizing the range of a real function class. Then, we point out that Sauer’s Lemma is valid for the discretized VC dimension. We group the real function classes having the infinite VC dimension into four categories by using the dis...
متن کاملPAC-Learning with General Class Noise Models
We introduce a framework for class noise, in which most of the known class noise models for the PAC setting can be formulated. Within this framework, we study properties of noise models that enable learning of concept classes of finite VC-dimension with the Empirical Risk Minimization (ERM) strategy. We introduce simple noise models for which classical ERM is not successful. Aiming at a more ge...
متن کاملA Theoretical Framework for Deep Transfer Learning
We generalize the notion of PAC learning to include transfer learning. In our framework, the linkage between the source and the target tasks is a result of having the sample distribution of all classes drawn from the same distribution of distributions, and by restricting all source and a target concepts to belong to the same hypothesis subclass. We have two models: an adversary model and a rand...
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:
- Arch. Math. Log.
دوره 54 شماره
صفحات -
تاریخ انتشار 2015