@inproceedings{www200945,
       booktitle = {18th International World Wide Web Conference},
           month = {April},
           title = {Nearest-Neighbor Caching for Content-Match Applications},
          author = {Sandeep Pandey and Andrei Broder and Flavio Chierichetti and Vanja Josifovski and Ravi Kumar and Sergei Vassilvitskii},
            year = {2009},
           pages = {441--441},
             url = {http://www2009.eprints.org/45/},
        abstract = {Motivated by contextual advertising systems and other web applications involving efficiency?accuracy tradeoffs, we study similarity caching. Here, a cache hit is said to occur if the requested item is similar but not necessarily equal to some cached item. We study two objectives that dictate the efficiency?accuracy tradeoff and provide our caching policies for these objectives. By conducting extensive experiments on real data we show similarity caching can signi?cantly improve the efficiency of contextual advertising systems, with minimal impact on accuracy. Inspired by the above, we propose a simple generative model that embodies two fundamental characteristics of page requests arriving to advertising systems, namely, long-range dependences and similarities. We provide theoretical bounds on the gains of similarity caching in this model and demonstrate these gains empirically by ?tting the actual data to the model.}
}