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...

Although usability is a broad subject, the literature relating to in-car navigation devices tends to focus primarily on efficiency of use. In this paper, we explore the neglected issue of learnability, that is the ease with which users learn to use, as well as some justification of its importance as a distinct issue. We present an evaluation method designed to identify learnability related prob...

We study the connections between determinacy of rational expectations equilibrium, and expectational stability or learnability of that equilibrium, in a relatively general New Keynesian model. Adoption of policies that induce both determinacy and learnability of equilibrium has been considered fundamental to successful policy in the literature. We ask what types of economic assumptions drive di...

In this paper we survey some results in inductive inference showing how learnability of a class of languages may depend on the hypothesis space chosen. Additionally, optimal hypothesis spaces, usable for every learnable class, are considered. We also discuss results which consider how learnability is effected if one requires learning using every suitable hypothesis space.

We study PAC learnability and stabilizability of Hedonic Games (HGs), i.e., efficiently inferring preferences or core-stable partitions from samples. first expand the known learnability/stabilizability landscape for some most prominent HGs classes, providing results Friends Enemies Games, Bottom Responsive, Anonymous HGs. Then, having a broader view in mind, we attempt to shed light on structur...

Bohannon and Stanowicz (1988) have claimed that contrary to popular belief, children do receive negative evidence about the ungrammaticality of their utterances in the form of recasts, expansions, and repetitions. Bohannon and Stanowicz argue that given such negative evidence, learnability theory shows that natural languages can be learned and that there is no need to postulate innate knowledge...

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....

The learnability of abstract syntactic principles Children acquiring language infer the correct form of syntactic constructions for which they appear to have little or no direct evidence, avoiding simple but incorrect generalizations that would be consistent with the data they receive. These generalizations must be guided by some inductive bias – some abstract knowledge – that leads them to pre...