On the Incommensurability Phenomenon
Suppose that two large, multi-dimensional data sets are each noisy measurements of the same underlying random process, and principle components analysis is performed separately on the data sets to reduce their dimensionality. In some circumstances it may happen that the two lower-dimensional data sets have an inordinately large Procrustean fitting-error between them. The purpose of this manuscript is to quantify this "incommensurability phenomenon." In particular, under specified conditions, the square Procrustean fitting-error of the two normalized lower-dimensional data sets is (asymptotically) a convex combination (via a correlation parameter) of the Hausdorff distance between the projection subspaces and the maximum possible value of the square Procrustean fitting-error for normalized data. We show how this gives rise to the incommensurability phenomenon, and we employ illustrative simulations as well as a real data experiment to explore how the incommensurability phenomenon may have an appreciable impact.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors
We introduce the URIEL knowledge base for massively multilingual NLP and the lang2vec utility, which provides information-rich vector identifications of languages drawn from typological, geographical, and phylogenetic da…
Language IdentificationLanguage ModelingLanguage ModellingMultilingual NLPOn the Notion that Language Models Reason
Language models (LMs) are said to be exhibiting reasoning, but what does this entail? We assess definitions of reasoning and how key papers in the field of natural language processing (NLP) use the notion and argue that …
Navigating Incommensurability Between Ethnomethodology, Conversation Analysis, and Artificial Intelligence
Like many research communities, ethnomethodologists and conversation analysts have begun to get caught up -- yet again -- in the pervasive spectacle of surging interests in Artificial Intelligence (AI). Inspired by discu…
Beyond Preferences in AI Alignment
The dominant practice of AI alignment assumes (1) that preferences are an adequate representation of human values, (2) that human rationality can be understood in terms of maximizing the satisfaction of preferences, and …
DescriptivePsychophysical laws as reflection of mental space properties
The paper is devoted to the relationship between psychophysics and physics of mind. The basic trends in psychophysics development are briefly discussed with special attention focused on Teghtsoonian's hypotheses. These h…