solidot新版网站常见问题,请点击这里查看。

Group Invariance and Computational Sufficiency. (arXiv:1807.05985v1 [math.ST])

来源于:arXiv
Statistical sufficiency formalizes the notion of data reduction. In the decision theoretic interpretation, once a model is chosen all inferences should be based on a sufficient statistic. However, suppose we start with a set of procedures rather than a specific model. Is it possible to reduce the data and yet still be able to compute all of the procedures? In other words, what functions of the data contain all of the information sufficient for computing these procedures? This article presents some progress towards a theory of "computational sufficiency" and shows that strong reductions can be made for large classes of penalized $M$-estimators by exploiting hidden symmetries in the underlying optimization problems. These reductions can (1) reveal hidden connections between seemingly disparate methods, (2) enable efficient computation, (3) give a different perspective on understanding procedures in a model-free setting. As a main example, the theory provides a surprising answer to the fo 查看全文>>