Research

One-Shot Localisation of the Global Minimum of a Noisy One-Dimensional Function: An Iterative Neural Minimizer Compared with Set Transformers and Classical Estimators

Single source1 source7 Oct 2026

arXiv:2604.03614v4 Announce Type: replace-cross Abstract: We study a passive form of global optimisation: from twenty noisy samples of an unknown one-dimensional function, predict where its global minimum lies, with no further queries.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2604.03614

← Back to all developments · Signals are a development reported by more than one source. See the methodology.