Priced Learning
نویسندگان
چکیده
In iterative learning the memory of the learner can only be updated when the hypothesis changes; this results in only finitely many updates of memory during the overall learning history. Priced learning relaxes this constraint on the update of memory by imposing some price on the updates of the memory – depending on the current datum – and requiring that the overall sum of the costs incurred has to be finite. There are priced-learnable classes which are not iteratively learnable. The current work introduces the basic definitions and results for priced learning. This work also introduces various variants of priced learning.
منابع مشابه
Optimistic Fair Priced Oblivious Transfer
Priced oblivious transfer (POT) is a two-party protocol between a vendor and a buyer in which the buyer purchases digital goods without the vendor learning what is bought. Although privacy properties are guaranteed, current schemes do not offer fair exchange. A malicious vendor can, e.g., prevent the buyer from retrieving the goods after receiving the payment, and a malicious buyer can also acc...
متن کاملRevisiting Robustness in Priced Timed Games
Priced timed games are optimal-cost reachability games played between two players—the controller and the environment—by moving a token along the edges of infinite graphs of configurations of priced timed automata. The goal of the controller is to reach a given set of target locations as cheaply as possible, while the goal of the environment is the opposite. Priced timed games are known to be un...
متن کاملSimple Priced Timed Games are not That Simple
Priced timed games are two-player zero-sum games played on priced timed automata (whose locations and transitions are labeled by weights modeling the costs of spending time in a state and executing an action, respectively). The goals of the players are to minimise and maximise the cost to reach a target location, respectively. We consider priced timed games with one clock and arbitrary (positiv...
متن کاملSocial Effects in Employer Learning: An Analysis of Siblings
This paper examines whether wages are based on information about personal contacts. I develop a theory of labor markets with imperfect information in which related workers have correlated abilities. I study wage setting under two alternative processes: individual learning, under which employers observe only a worker’s own characteristics, and social learning, under which employers also observe ...
متن کاملConcavely-Priced Probabilistic Timed Automata
Concavely-priced probabilistic timed automata, an extension of probabilistic timed automata, are introduced. In this paper we consider expected reachability, discounted, and average price problems for concavely-priced probabilistic timed automata for arbitrary initial states. We prove that these problems are EXPTIME-complete for probabilistic timed automata with two or more clocks and PTIME-com...
متن کامل