| ▲ | cubefox 3 days ago |
| What about sampling at low resolution? If the hills and valleys aren't too close together, this should give a good indication of where the global minimum is. |
|
| ▲ | xigoi 3 days ago | parent [-] |
| > If the hills and valleys aren't too close together That’s a big “if”. |
| |
| ▲ | cubefox 3 days ago | parent [-] | | At least it will catch those valleys that are wider than the sampling resolution. | | |
| ▲ | xigoi 3 days ago | parent [-] | | Yeah. The problem is that the number of samples needed is exponential in the dimension, so in a 1000-dimensional space, you won’t even be able to subdivide it into 2×…×2. | | |
|
|
