A Genetic Algorithm for Obtaining Memory Constrained Near-Perfect Hashing

TL;DR

This paper introduces a genetic algorithm-based method to optimize near-perfect hash functions, achieving faster search times with less memory in memory-constrained environments.

Contribution

It presents a novel approach combining non-linear transformations and genetic algorithms to improve near-perfect hashing efficiency.

Findings

Near-perfect hashing outperforms binary search in speed.

The method uses less memory than perfect hashing.

Genetic algorithm effectively finds optimal hash parameters.

Abstract

The problem of fast items retrieval from a fixed collection is often encountered in most computer science areas, from operating system components to databases and user interfaces. We present an approach based on hash tables that focuses on both minimizing the number of comparisons performed during the search and minimizing the total collection size. The standard open-addressing double-hashing approach is improved with a non-linear transformation that can be parametrized in order to ensure a uniform distribution of the data in the hash table. The optimal parameter is determined using a genetic algorithm. The paper results show that near-perfect hashing is faster than binary search, yet uses less memory than perfect hashing, being a good choice for memory-constrained applications where search time is also critical.