Second-order induction in prediction problems

Rossella Argenziano

doi:10.1073/pnas.1901597116

Second-order induction in prediction problems

2019-05-07

2

OA

AI

DOI：10.1073/pnas.1901597116

原文链接

查看原文

摘要

En 中文

Agents make predictions based on similar past cases, while also learning the relative importance of various attributes in judging similarity. We ask whether the resulting empirically optimal similarity function (EOSF) is unique and how easy it is to find it. We show that with many observations and few relevant variables, uniqueness holds. By contrast, when there are many variables relative to observations, nonuniqueness is the rule, and finding the EOSF is computationally hard. The results are interpreted as providing conditions under which rational agents who have access to the same observations are likely to converge on the same predictions and conditions under which they may entertain different probabilistic beliefs.

Keyword:

belief formation

empirically optimal similarity function

learning

kernel estimation

generalized context model

Second-order induction in prediction problems

摘要

AI总结

期刊

机构