mohamad maheri
|
c701e2c338
|
only consider positive interaction for task embedding
|
2 years ago |
mohamad maheri
|
5273533fc8
|
Revert "deep kmeans loss"
This reverts commit b4d130e2
|
2 years ago |
mohamad maheri
|
07bb1cd89a
|
check result of hyper tuning (best_result1)
|
2 years ago |
mohamad maheri
|
3a3b256e65
|
Revert "prepare for hyper parameter tuning"
This reverts commit 576c0e97
|
2 years ago |
mohamad maheri
|
b4d130e28e
|
deep kmeans loss
|
2 years ago |
mohamad maheri
|
dc38c4018f
|
tanp loss (kl loss)
|
2 years ago |
mohamad maheri
|
acacb68d33
|
tanp loss (kl loss)
|
2 years ago |
mohamad maheri
|
d425ba0c97
|
cluster loss (try to hard assignment)
|
2 years ago |
mohamad maheri
|
576c0e97f2
|
prepare for hyper parameter tuning
|
2 years ago |
mohamad maheri
|
d2d5563db1
|
prepare for hyper parameter tuning
|
2 years ago |
mohamad maheri
|
908149d81b
|
task encoder consider item's score
there is problems that should set inner loop larger than one
|
2 years ago |
mohamad maheri
|
d9e027a938
|
user clustering effects prediction network's weights
|
2 years ago |
mohamad maheri
|
01b24e10bf
|
generic algorithms and parameters
|
3 years ago |
mohamad maheri
|
a23a4ec823
|
generic algorithms and parameters
|
3 years ago |
mohamad maheri
|
a9d1772942
|
other hyper parameters
|
3 years ago |
mohamad maheri
|
153f3b982f
|
prepare to run on a cpu
|
3 years ago |
mohamad maheri
|
a4e913f57a
|
GBML + some optimization for cuda memory
|
3 years ago |
mohamad maheri
|
0d298f3f31
|
melu by l2l + MetaSGD + second oreder
|
3 years ago |
mohamad maheri
|
14e32e0afc
|
melu by l2l + MetaSGD
|
3 years ago |
mohamad maheri
|
00555ed067
|
melu by l2l + MetaSGD
|
3 years ago |