Reformulating van Rijsbergen's $F_{\beta}$ metric for weighted binary cross-entropy. (arXiv:2210.16458v1 [stat.ML])

The separation of performance metrics from gradient based loss functions may
not always give optimal results and may miss vital aggregate information. This
paper investigates incorporating a performance metric alongside differentiable
loss functions to inform training outcomes. The goal is to guide model
performance and interpretation by assuming statistical distributions on this
performance metric for dynamic weighting. The focus is on van Rijsbergens
$F_{\beta}$ metric -- a popular choice for gauging classification performance.
Through distributional assumptions on the $F_{\beta}$, an …

arxiv beta binary cross-entropy entropy