AI RESEARCH

Efficient Parameter Estimation of Truncated Boolean Product Distributions

arXiv CS.LG

ArXi:2007.02392v3 Announce Type: replace We study the problem of estimating the parameters of a Boolean product distribution in $d$ dimensions, when the samples are truncated by a set $S \subset \{0, 1\}^d$ accessible through a membership oracle. This is the first time that the computational and statistical complexity of learning from truncated samples is considered in a discrete setting.