Skip to content
Snippets Groups Projects
Commit 170d54ae authored by iago-lito's avatar iago-lito
Browse files

Optimize likelihood with torch. 

- Extend calculations by abstracting over `f64` and  `tch::Tensors`.
- The "free parameters" distinction vanishes
  in favour of gradient-tracking declaration.
- Have the calculation leaves step back from `Parameters` to `Scores`,
  ranging freely over the real line.
- Possibly move calculations to CUDA.
parent 16533383
Hide whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment