Zongyuan Tan, Hongya Wang, Bo Xu, Minjie Luo, Ming Du
TL;DR通过随机抽样和随机投影的组合,FastLSH 算法将 LSH 计算的时间复杂度从 O (n) 降低到 O (m)(其中 m < n),并具有可证明的 LSH 属性,是一种有希望替代经典 LSH 方案的方法。
Abstract
locality-sensitive hashing (lsh) is an effective randomized technique widely
used in many machine learning tasks. The cost of hashing is proportional to
data dimensions, and thus often the performance bottleneck