Scalable balanced k -d tree construction for distributed data
View Full Paper
Ask AI
Bookmark
Share
Discussion
Loading...
Member takes
Overview
Randomized trial demonstrates efficient k-d tree construction in distributed datasets, highlighting scalability benefits.
Key Points
The aim is to present a scalable method for constructing k-d trees from distributed datasets while ensuring efficient memory usage and construction time.
Introduced a new MapReduce algorithm for k-d tree construction.
Achieved O(N) construction time and O(1) memory usage.
Outlined theoretical bounds on the quality of median approximations.
Simulation studies showed the method achieves both accuracy and scalability.
Demonstrated applicability in distributed M-estimation for regression.