Re:Neural programmer better than Quicksort
by algo_trader on Friday July 10, 2020 @08:02AM
(#23790635)
> neural program induction in compilers to try generate faster implementations
Can u provide more details?
I am familiar with garden-variety ML-optimization-of-combinatorical-space in compilers.
How would u even "measure" the expected performance unless these are gradual greedy changes
There’s some cool work on using neural program induction in compilers to try generate faster implementations based off the ‘oracle’ program that’s being compiled.