The limitations of the theoretical analysis of applied algorithms
share
The theoretical analysis of performance has been an important tool in the engineering of algorithms in many application domains. Its goals are to predict the empirical performance of an algorithm and to be a yardstick that drives the design of novel algorithms that perform well in practice. While these goals have been achieved in many instances, they have not been achieved in some other crucial application domains. In this paper, I focus on the example of sequencing bioinformatics, an inter-disciplinary field that uses algorithms to extract biological meaning from genome sequencing data. I will demonstrate two concrete examples of how theoretical analysis has failed to achieve its goals but also give one encouraging example of success. I will then catalog some of the challenges of applying theoretical analysis to sequencing bioinformatics, argue why empirical analysis is not enough, and give a vision for improving the relevance of theoretical analysis to sequencing bioinformatics and other application domains. By recognizing the problem, understanding its roots, and providing potential solutions, this work can hopefully be a crucial first step towards making theoretical analysis more relevant in modern application domains.
READ FULL TEXT