Bayesian error propagation for neural-net based parameter inference

Understand

Neural nets have become popular to accelerate parameter inferences, especially for the upcoming generation of galaxy surveys in cosmology.

• As neural nets are approximative by nature, a recurrent question has been how to propagate the neural net's approximation error, in order to avoid biases in the parameter inference.
• We present a Bayesian solution to propagating a neural net's approximation error and thereby debiasing parameter inference.
• We exploit that a neural net reports its approximation errors during the validation phase.