Math OverflowError in update_factors

[danielegrattarola]

Hello,
I'm trying to use you code to learn and predict on a binary sparse matrix (meaning I only have 1s in the matrix), but during the training phase it will crash and throw this error:
Traceback (most recent call last): File "bpr.py", line 260, in <module> model.train(data,sampler,num_iters) File "bpr.py", line 52, in train self.update_factors(u,i,j) File "bpr.py", line 81, in update_factors z = 1.0/(1.0+exp(x)) OverflowError: math range error

I've checked to see who's guilty of this, and apparently the x variable of the fucntion is diverging, therefore causing the exp operator to overflow.
Have you encountered this issue? Can you suggest a fix?

Thanks

[YadalaRamya]

What is the input data for bpr.py code?? can u provide a sample input

[HongxuChenUQ]

sampling 9993 <user,item i,item j> triples...
initial loss = 5242.5237869
starting iteration 0
Traceback (most recent call last):
File "testTopK.py", line 303, in
model.train(data,sampler,num_iters)
File "testTopK.py", line 52, in train
self.update_factors(u,i,j)
File "testTopK.py", line 80, in update_factors
z = 1.0/(1.0+exp(x))
OverflowError: math range error

Same problem, Any ideas?

[HongxuChenUQ]

Hi, please try this to fix
try:
z = 1.0/(1.0+exp(x))
except OverflowError:
z = float('inf')

[fukien]

I met the same problem, and I tune the learning rate smaller to resolve the math range error