Learning sparse mixtures of rankings from noisy information
This provides an efficient solution for learning ranking mixtures in noisy settings, which is incremental but addresses a computational bottleneck in ranking analysis.
The paper tackles the problem of learning an unknown mixture of k rankings from noisy samples, achieving high accuracy with an algorithm that runs in n^{O(log k)} time, improving upon previous exponential-time methods.
We study the problem of learning an unknown mixture of $k$ rankings over $n$ elements, given access to noisy samples drawn from the unknown mixture. We consider a range of different noise models, including natural variants of the "heat kernel" noise framework and the Mallows model. For each of these noise models we give an algorithm which, under mild assumptions, learns the unknown mixture to high accuracy and runs in $n^{O(\log k)}$ time. The best previous algorithms for closely related problems have running times which are exponential in $k$.