for use in learning algorithms whose optimal solutions are guaranteed only for Mercer kernels. We demonstrate our algorithm on object recognition tasks and show it to be accurate and dramatically faster than current approaches.

generalizing function approximator such as a neural net. Although this has been successful in the domain of backgammon, there is no guarantee of convergence. In this paper, we show that the combination of dynamic programming and function approximation is not robust, and in even very benign cases, may produce

is a modification of the GVA, utilizes reservation prices of auctioned goods for making decisions on whether to sell goods in a bundle or separately. The LDS protocol satisfies individual rationality and incentive compatibility, although it is not guaranteed to achieve a Pareto efficient social

be learned rapidly with a locally weighted regression technique with guaranteed convergence of the learning algorithm and convergence to the movement target. This property makes the system suitable for movement imitation and also for classifying demonstrated movement according to the parameters

aligning its desiderata with the incentives of all its players, including colluders, to a signi cant and mutually bene cial extent. Of course such mechanisms may exist only for suitable desiderata. In unrestricted combinatorial auctions, where classical mechanisms essentially guarantee 0 social welfare

We describe mechanisms for auctions that are simultaneously truthful (alternately known as strategy-proof or incentive-compatible) and guarantee high "net" profit. We make use of appropriate variants of competitive analysis of algorithms in designing and analyzing our mechanisms. Thus, we

of the proposed algorithms are proven to guarantee convergence to a conflict-free assignment, and it is shown that the converged solutions exhibit provable worst-case performance. It is also demonstrated that CBAA and CBBA produce conflict-free feasible solutions that are robust to both inconsistencies

ABSTRACT Incentives play a crucial role in BitTorrent, motivating users to upload to others to achieve fast download times for all peers. Though long believed to be robust to strategic manipulation, recent work has empirically shown that BitTorrent does not provide its users incentive to follow

valuations) that no mechanism can be better than 3/2-competitive (2-competitive) for revenue (efficiency). Our general approach considers a learning phase followed by an accepting phase, and is careful to handle incentive issues for agents that span the two phases. We extend to the k > 1 case, by deriving

the problem of finding a robust solution of maximum revenue. A weighted super solution guarantees that any subset of bids likely to be withdrawn can be repaired to form a new solution of at least a given revenue by making a limited number of changes. Secondly, we introduce an auction model that uses a form