AI RESEARCH
The Rashomon Effect for Visualizing High-Dimensional Data
arXiv CS.LG
•
ArXi:2604.00485v1 Announce Type: new Dimension reduction (DR) is inherently non-unique: multiple embeddings can preserve the structure of high-dimensional data equally well while differing in layout or geometry. In this paper, we formally define the Rashomon set for DR -- the collection of `good' embedding -- and show how embracing this multiplicity leads to powerful and trustworthy representations. Specifically, we pursue three goals. First, we