This article was originally published with errors in some of the equations.
In algorithm 1 on page 4 there are two errors,
$ {\boldsymbol{\theta}}_{\boldsymbol{i}}^{\left(\boldsymbol{0}\right)}\leftarrow \arg \underset{\boldsymbol{\theta}}{\min }{\sum}_{k=1}^Np\left({\boldsymbol{Y}}_{\boldsymbol{k}}|\boldsymbol{\theta} \right) $
should have read
$ {\boldsymbol{\theta}}_{\boldsymbol{i}}^{\left(\boldsymbol{0}\right)}\leftarrow \arg \underset{\boldsymbol{\theta}}{\min }-{\sum}_{k=1}^N\log\;p\left({\boldsymbol{Y}}_{\boldsymbol{k}}|\boldsymbol{\theta} \right) $
and
$ {\rho}^{(b)}\leftarrow \arg\;{\min}_{\rho }{\sum}_{i=1}^Np\left({\boldsymbol{Y}}_{\boldsymbol{i}}|{\boldsymbol{\theta}}_{\boldsymbol{i}}^{\left(\boldsymbol{b}-\boldsymbol{1}\right)}-\rho \cdot {f}^{(b)}\left({\boldsymbol{X}}_{\boldsymbol{i}}\right)\right) $
, should have read
$ {\rho}^{(b)}\leftarrow \arg\;{\min}_{\rho }-{\sum}_{i=1}^N\log\;p\left({\boldsymbol{Y}}_{\boldsymbol{i}}|{\boldsymbol{\theta}}_{\boldsymbol{i}}^{\left(\boldsymbol{b}-\boldsymbol{1}\right)}-\rho \cdot {f}^{(b)}\left({\boldsymbol{X}}_{\boldsymbol{i}}\right)\right) $
.
In Section 5.2 on page 11, the equation
$ \frac{1}{N}{\sum}_i\log\;p\left({Y}_i|{X}_i\right) $
, should have read
$ -\frac{1}{N}{\sum}_i\log\;p\left({Y}_i|{X}_i\right) $
.
The authors apologise for these errors.