Uniform Convergence and Learnability
نویسندگان
چکیده
5.3 Approximating Stochastic Concepts by Functions ............................... 88 5.4 Classification Noise and Semi-Consistent Learning ..............................96 6. N on-U niform L earnab ility ...........................................................................98 6.1 The Notion of Non-Uniform L earnab ility ................................................98 6.2 Distribution-Independent Learnability ...................................................100 6.3 Distribution-Dependent L earnab ility ......................................................101 7. Learning Form al C o n c ep ts ........................................................................115 7.
منابع مشابه
Uniform 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 کاملStochastic Convex Optimization
For supervised classification problems, it is well known that learnability is equivalent to uniform convergence of the empirical risks and thus to learnability by empirical minimization. Inspired by recent regret bounds for online convex optimization, we study stochastic convex optimization, and uncover a surprisingly different situation in the more general setting: although the stochastic conv...
متن کاملLearnability, Stability and Uniform Convergence
The problem of characterizing learnability is the most basic question of statistical learning theory. A fundamental and long-standing answer, at least for the case of supervised classification and regression, is that learnability is equivalent to uniform convergence of the empirical risk to the population risk, and that if a problem is learnable, it is learnable via empirical risk minimization....
متن کاملLearnability and Stability in the General Learning Setting
We establish that stability is necessary and sufficient for learning, even in the General Learning Setting where uniform convergence conditions are not necessary for learning, and where learning might only be possible with a non-ERM learning rule. This goes beyond previous work on the relationship between stability and learnability, which focused on supervised classification and regression, whe...
متن کاملOnline Learning: Random Averages, Combinatorial Parameters, and Learnability
We study learnability in the online learning model. We define several complexity measures which capture the difficulty of learning in a sequential manner. Among these measures are analogues of Rademacher complexity, covering numbers and fat shattering dimension from statistical learning theory. Relationship among these complexity measures, their connection to online learning, and tools for boun...
متن کامل