(Waterfall et al., 2006): Proposes that sloppy models belong to a common "universality class" with eigenvalue spectra that are roughly constant on a logarithmic scale.
In scientific literature, a "sloppy" model refers to a complex multiparameter system where model behavior is highly sensitive to only a few "stiff" parameter combinations, while the majority of "sloppy" directions in parameter space have almost no effect on model predictions. sloppy
: A few parameter combinations ("stiff") tightly constrain model behavior, while others ("sloppy") can vary by orders of magnitude without changing the output. (Waterfall et al
: The set of all possible model predictions forms a "manifold" that is often extremely narrow in some dimensions, resembling a "hyper-ribbon". Other Contexts of "Sloppy" in Research : The set of all possible model predictions
Below are several major papers and resources that define the field:
(Machta et al., 2013): Explains why complicated microscopic processes often result in simple macroscopic behavior. Core Concepts of "Sloppy" Research