Computational Implications of Reducing Data to Sufficient Statistics
Computation
2015-07-31 v3 Information Theory
Machine Learning
math.IT
Abstract
Given a large dataset and an estimation task, it is common to pre-process the data by reducing them to a set of sufficient statistics. This step is often regarded as straightforward and advantageous (in that it simplifies statistical analysis). I show that -on the contrary- reducing data to sufficient statistics can change a computationally tractable estimation problem into an intractable one. I discuss connections with recent work in theoretical computer science, and implications for some techniques to estimate graphical models.
Cite
@article{arxiv.1409.3821,
title = {Computational Implications of Reducing Data to Sufficient Statistics},
author = {Andrea Montanari},
journal= {arXiv preprint arXiv:1409.3821},
year = {2015}
}
Comments
20 pages