We present an algorithm for improving the accuracy of algorithms for learning binary concepts. The improvement is achieved by combining a large number of hypotheses, each of which is generated by training the given learning algorithm on a different set of examples. Our algorithm is based on ideas presented by Schapire in his paper "The strength of weak learnability", and represents an improvement over his results. The analysis of our algorithm provides general upper bounds on the resources required for learning in Valiant's polynomial PAC learning framework, which are the best general upper bounds known today. We show that the number of hypotheses that are combined by our algorithm is the smallest number possible. Other outcomes of our analysis are results regarding the representational power of threshold circuits, the relation between learnability and compression, and a method for parallelizing PAC learning algorithms. We provide extensions of our algorithms to cases in which the conc...

We consider an environment where distributed data sources continuously stream updates to a centralized processor that monitors continuous queries over the distributed data. Significant communication overhead is incurred in the presence of rapid update streams, and we propose a new technique for reducing the overhead. Users register continuous queries with precision requirements at the central stream processor, which installs filters at remote data sources. The filters adapt to changing conditions to minimize stream rates while guaranteeing that all continuous queries still receive the updates necessary to provide answers of adequate precision at all times. Our approach enables applications to trade precision for communication overhead at a fine granularity by individually adjusting the precision constraints of continuous queries over streams in a multi-query workload.

In this paper, we examine how the complexity of domain-independent planning with STRIPS-style operators depends on the nature of the planning operators. We show

Abstract not found

Caching approximate values instead of exact values presents an opportunity for performance gains in exchange for decreased precision. To maximize the performance improvement, cached approximations must be of appropriate precision: approximations that are too precise easily become invalid, requiring frequent refreshing, while overly imprecise approximations are likely to be useless to applications, which must then bypass the cache. We present a parameterized algorithm for adjusting the precision of cached approximations adaptively to achieve the best performance as data values, precision requirements, or workload vary. We consider interval approximations to numeric values but our ideas can be extended to other kinds of data and approximations. Our algorithm strictly generalizes previous adaptive caching algorithms for exact copies: we can set parameters to require that all approximations be exact, in which case our algorithm dynamically chooses whether or not to cache each data value. We have implemented our algorithm and tested it on synthetic and real-world data. A number of experimental results are reported, showing the effectiveness of our algorithm at maximizing performance, and also showing that in the special case of exact caching our algorithm performs as well as previous algorithms. In cases where bounded imprecision is acceptable, our algorithm easily outperforms previous algorithms for exact caching. 1

We discuss several complexity measures for Boolean functions: certificate complexity, sensitivity, block sensitivity, and the degree of a representing or approximating polynomial. We survey the relations and biggest gaps known between these measures, and show how they give bounds for the decision tree complexity of Boolean functions on deterministic, randomized, and quantum computers. 1 Introduction Computational Complexity is the subfield of Theoretical Computer Science that aims to understand "how much" computation is necessary and sufficient to perform certain computational tasks. For example, given a computational problem it tries to establish tight upper and lower bounds on the length of the computation (or on other resources, like space). Unfortunately, for many, practically relevant, computational problems no tight bounds are known. An illustrative example is the well known P versus NP problem: for all NP-complete problems the current upper and lower bounds lie exponentially ...

The purpose of this paper is to show how the introduction of new primitive constraints (e.g. among, diffn, cycle) over finite domains in the constraint logic programming system CHIP result in finding very rapidly good solutions for a large class of difficult sequencing, scheduling, geometrical placement and vehicle routing problems. The among constraint allows to specify sequencing constraints in a very concise way. For the first time, the diffn constraint allows to express and to solve directly multidimensional placement problems where one has to consider non overlapping constraints between n-dimensional objects (e.g. rectangles, parallelepipeds). The cycle constraint makes possible to specify a wide range of graph partitioning problems that could not yet be expressed by using current constraint logic programming languages. One of the main advantage of all these new primitives is to take into account more globally a set of elementary constraints. Finally, we point out that all the previous primitive constraints enhance the power of the CHIP system significantly, allowing to solve real life problems that were not within reach of constraint technology before. 1

Strict consistency of replicated data is infeasible or not required by many distributed applications, so current systems often permit stale replication,inwhich cached copies of data values are allowed to become out of date. Queries over cached data return an answer quickly, but the stale answer may be unboundedly imprecise. Alternatively, queries over remote master data return a precise answer, but with potentially poor performance. To bridge the gap between these two extremes, we propose a new class of replication systems called TRAPP (Tradeoff in Replication Precision and Performance). TRAPP systems give each user fine-grained control over the tradeoff between precision and performance: Caches store ranges that are guaranteed to bound the current data values, instead of storing stale exact values. Users supply a quantitative precision constraint along with each query. To answer a query, TRAPP systems automatically select a combination of locally cached bounds and exact master data stored remotely to deliver a bounded answer consisting of a range that is no wider than the specified precision constraint, that is guaranteed to contain the precise answer, and that is computed as quickly as possible. This paper defines the architecture of TRAPP replication systems and covers some mechanics of caching data ranges. It then focuses on queries with aggregation, presenting optimization algorithms for answering queries with precision constraints, and reporting on performance experiments that demonstrate the fine-grained control of the precision-performance tradeoff offered by TRAPP systems.

In this paper, we show that in the best-known version of the blocks world (and several related versions), planning is difficult, in the sense that finding an optimal plan is NP-hard. However, the NP-hardness is not due to deleted-condition interactions, but instead due to a situation which we call a deadlock. For problems that do not contain deadlocks, there is a simple hill-climbing strategy that can easily find an optimal plan, regardless of whether or not the problem contains any deleted-condition interactions. The above result is rather surprising, since one of the primary roles of the blocks world in the planning literature has been to provide examples of deleted-condition interactions such as creative destruction and Sussman's anomaly. However, we can explain why deadlocks are hard to handle in terms of a domain-independent goal interaction which we call an enabling-condition interaction, in which an action invoked to achieve one goal has a side-effect of making it easier to achi...

Besides an elementary introduction to q-identities and basic hypergeometric series, a newly developed Mathematica implementation of a q-analogue of Zeilberger's fast algorithm for proving terminating q-hypergeometric identities together with its theoretical background is described. To illustrate the usage of the package and its range of applicability, non-trivial examples are presented as well as additional features like the computation of companion and dual identities.