Algorithm evaluation is the process of assessing a property or properties of an algorithm.
Motivation and Background
It is often valuable to assess the efficacy of an algorithm. In many cases, such assessment is relative, that is, evaluating which of several alternative algorithms is best suited to a specific application.
Processes and Techniques
Many learning algorithms have been proposed. In order to understand the relative merits of these alternatives, it is necessary to evaluate them. The primary approaches to evaluation can be characterized as either theoretical or experimental. Theoretical evaluation uses formal methods to infer properties of the algorithm, such as its computational complexity (Papadimitriou, 1994), and also employs the tools of computational learning theory to assess learning theoretic properties. Experimental evaluation applies the algorithm to learning tasks to study its performance in practice.
There are many different types of property that may be...
- Webb, G. I. (2000). MultiBoosting: A technique for combining boosting and wagging. Machine Learning, 40(2), 159–196.Google Scholar