Re:FunSearch: Making new discoveries in mathematical science...
by lossolo on Thursday December 14, 2023 @04:41PM
(#38647668)
From the paper:
We note that FunSearch currently works best for problems having the following characteristics:
a) availability of an efficient evaluator; b) a “rich” scoring feedback quantifying the improvements
(as opposed to a binary signal); c) ability to provide a skeleton with an isolated part to be evolved.
For example, the problem of generating proofs for theorems [52–54] falls outside this scope, since
it is unclear how to provide a rich enough scoring signal.
We note that FunSearch currently works best for problems having the following characteristics: a) availability of an efficient evaluator; b) a “rich” scoring feedback quantifying the improvements (as opposed to a binary signal); c) ability to provide a skeleton with an isolated part to be evolved. For example, the problem of generating proofs for theorems [52–54] falls outside this scope, since it is unclear how to provide a rich enough scoring signal.