Any four real numbers are on all fours with analogy
This provides mathematical foundations for analogy in AI and machine learning, where it is used for inference and representation assessment, but it is incremental as it builds on existing generalized means concepts.
The paper tackles the problem of formalizing analogy for numerical representations by proposing a unifying view based on generalized means, showing that any four increasing positive real numbers can be expressed as an analogy with a unique power parameter and that such analogies can be reduced to arithmetic analogies.
This work presents a formalization of analogy on numbers that relies on generalized means. It is motivated by recent advances in artificial intelligence and applications of machine learning, where the notion of analogy is used to infer results, create data and even as an assessment tool of object representations, or embeddings, that are basically collections of numbers (vectors, matrices, tensors). This extended analogy use asks for mathematical foundations and clear understanding of the notion of analogy between numbers. We propose a unifying view of analogies that relies on generalized means defined in terms of a power parameter. In particular, we show that any four increasing positive real numbers is an analogy in a unique suitable power. In addition, we show that any such analogy can be reduced to an equivalent arithmetic analogy and that any analogical equation has a solution for increasing numbers, which generalizes without restriction to complex numbers. These foundational results provide a better understanding of analogies in areas where representations are numerical.