Coupling layers

[vmoens]

Adds Coupling layers.

### Test plan

from flowtorch.parameters.coupling import DenseCoupling, ConvCoupling
from flowtorch.bijectors.coupling import CouplingBijector as Coupling, ConvCouplingBijector
import torch
torch.set_default_dtype(torch.double)

def test():
    d = DenseCoupling()
    c = Coupling(d)
    c = c(shape=torch.Size([32,]))
    for p in c.parameters():
        p.data += torch.randn_like(p)/10
    x = torch.randn(1, 32,requires_grad=True)
    y = c.forward(x)
    yd = y.detach_from_flow()
    x_bis = c.inverse(yd)
    torch.testing.assert_allclose(x, x_bis)
    
    torch.testing.assert_allclose(
        c.log_abs_det_jacobian(x, y), 
        c.log_abs_det_jacobian(x, yd)
    )
    
test()

[stefanwebb]

This is really fantastic - I think it's almost there! Let's have a chat offline about coupling transforms, I think there may be a few ways to interpret them from the literature

[codecov-commenter]

Codecov Report

Merging #92 (54b4078) into main (4992731) will increase coverage by 0.04%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main      #92      +/-   ##
==========================================
+ Coverage   98.25%   98.29%   +0.04%     
==========================================
  Files           6        6              
  Lines         229      235       +6     
==========================================
+ Hits          225      231       +6     
  Misses          4        4              

Flag	Coverage Δ
unittests	98.29% <100.00%> (+0.04%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
tests/test_bijectivetensor.py	98.64% <ø> (ø)
tests/test_bijector.py	100.00% <100.00%> (ø)
tests/test_distribution.py	100.00% <100.00%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 4992731...54b4078. Read the comment docs.

[facebook-github-bot]

Hi @vmoens!

Thank you for your pull request.

We require contributors to sign our Contributor License Agreement, and yours needs attention.

You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!