Nearly Maximally Predictive Features and Their Dimensions
From MaRDI portal
Publication:6283702
arXiv1702.08565MaRDI QIDQ6283702FDOQ6283702
Authors: Sarah E. Marzen, James P. Crutchfield 
Publication date: 27 February 2017
Abstract: Scientific explanation often requires inferring maximally predictive features from a given data set. Unfortunately, the collection of minimal maximally predictive features for most stochastic processes is uncountably infinite. In such cases, one compromises and instead seeks nearly maximally predictive features. Here, we derive upper-bounds on the rates at which the number and the coding cost of nearly maximally predictive features scales with desired predictive power. The rates are determined by the fractal dimensions of a process' mixed-state distribution. These results, in turn, show how widely-used finite-order Markov models can fail as predictors and that mixed-state predictive features offer a substantial improvement.
This page was built for publication: Nearly Maximally Predictive Features and Their Dimensions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6283702)
