D. Levin

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

The Neural Function Minimizer is introduced, an iterative model that walks a position across the domain and, at every step, reads the samples near that position and attends to all twenty of them, and is compared with two Set Transformers of the same size, one that answers with a single point and one that answers with a...