solidot新版网站常见问题,请点击这里查看。
消息
本文已被查看100次
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>>