Near-Optimal Sample Compression for Nearest Neighbors
Lee-Ad J. Gottlieb, Aryeh Kontorovich, Pinhas Nisnevitch · IEEE Transactions on Information Theory · 2018
We present the first sample compression algorithm for nearest neighbors with non-trivial performance guarantees. We complement these guarantees by demonstrating almost matching hardness lower bounds, which show that our performance bound is nearly optimal. Our result yields new insight into margin-based nearest neighbor classification in metric spaces and allows us to significantly sharpen and simplify existing bounds. Some encouraging empirical results are also presented.