Timezone: »

Ultra Fast Medoid Identification via Correlated Sequential Halving
Tavor Baharav · David Tse

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #41

The medoid of a set of n points is the point in the set that minimizes the sum of distances to other points. It can be determined exactly in O(n^2) time by computing the distances between all pairs of points. Previous works show that one can significantly reduce the number of distance computations needed by adaptively querying distances. The resulting randomized algorithm is obtained by a direct conversion of the computation problem to a multi-armed bandit statistical inference problem. In this work, we show that we can better exploit the structure of the underlying computation problem by modifying the traditional bandit sampling strategy and using it in conjunction with a suitably chosen multi-armed bandit algorithm. Four to five orders of magnitude gains over exact computation are obtained on real data, in terms of both number of distance computations needed and wall clock time. Theoretical results are obtained to quantify such gains in terms of data parameters. Our code is publicly available online at https://github.com/TavorB/Correlated-Sequential-Halving.

Author Information

Tavor Baharav (Stanford University)

I am a second year PhD student in Electrical Engineering at Stanford University working with Professor David Tse, recently on developing fast (near linear time) randomized algorithms using techniques from multi-armed bandits. I am grateful to be supported by the NSF Graduate Research Fellowship and the Stanford Graduate Fellowship (SGF). I graduated from UC Berkeley in May 2018 where I studied Electrical Engineering and Computer Science. In my time there, I was fortunate to get the chance to work with Professor Kannan Ramchandran on coding theory and its applications to distributed computing. My current research focus is on constructing algorithms that adapt to problem instance difficulty, and more broadly in randomized algorithms, machine learning, multi-armed bandits, and their applications in engineering and computational biology problems.

David Tse (Stanford University)

More from the Same Authors