Author

Pengcheng Xie

1 paper indexed here

Fetches their full publication history.

Not the right person? Other researchers publish under this name.

#software testing Preprint Aug 2026

Why and When Neural Networks Improve Local Approximation in Optimization

It is shown that the contradiction in experience with neural surrogates in derivative-free optimisation dissolves once three factors are stated, and that these, rather than the fit accuracy a training curve reports, are what delimit when a learned local model pays.

Cheng Bian, Pengcheng Xie · 0 citations