Closed BuenoRuben closed 3 months ago
Merging #140 (63672d4) into main (ff06a8b) will decrease coverage by
14.16%
. The diff coverage is98.87%
.
Now the constraints are always verified and the loss decreases when tradeoff=0
.
However, when tradeoff is different from 0, the loss oscillates... So there is still a problem.
I managed to make the loss decrease when we have a tradeoff, but the conmition of one of the matrix being identity is still not solved, however the decision boundaries are closer to those of TCA, so we should be fine, however I don't understand why before, when the loss was oscillating, we had a better adapter (we had 100% acc)
see: https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=a279f53f386ac78345b67e13c1808880c718efdf#page=3&zoom=100,144,841