Year: 2018
Type: preprint
Abstract: This paper presents a simple extension of the binary heap, the List Heap. We use List Heaps to demonstrate the idea of adaptive heaps: heaps whose performance is a function of both the size of the problem instance and the disorder of the problem instance. We focus on the presortedness of the input sequence as a measure of disorder for the problem instance. A number of practical applications that rely on heaps deal with input that is not random. Even random input contains presorted subsequences. Devising heaps that exploit this structure may provide a means for improving practical performance. We present some basic empirical tests to support this claim. Additionally, adaptive heaps may provide an interesting direction for theoretical investigation.
Source: arXiv (Cornell University)
Author: Frohmader, Andrew
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4394669796