I have an array of time of arrivals and I want to convert it to count data using pytorch in a differentiable way.

Example arrival times:

arrival_times = [2.1, 2.9, 5.1]

and let's say the total range is 6 seconds. What I want to have is:

counts = [0, 0, 2, 2, 2, 3]

For this task, a non-differentiable way works perfect:

x = [1, 2, 3, 4,5,6] counts = torch.sum(arrival_times[:, None] < torch.Tensor(x), dim=0) 

It turns out the < operation here is not differentiable. I need a differentiable approximation of this operation.

What I could think of is to subtract the x from arrival_times with broadcasting which leads the following array.

[ [1.1, 0.1, -0.9, -1.9, -2.9, -3.9] [1.9, 0.9, -0.1, -1.1, -2.1, -3.1] [4.1, 3.1, 2.1, 1.1, 0.1, -0.9] ] 

And then somehow count the number of negative (and also zero preferably) elements vertically which will give us the counts [0, 0, 2, 2, 2, 3].

Is there a way to do this or completely new idea for such approximation?

I have an array of time of arrivals and I want to convert it to count data using pytorch in a differentiable way.

Example arrival times:

arrival_times = [2.1, 2.9, 5.1]

and let's say the total range is 6 seconds. What I want to have is:

counts = [0, 0, 2, 2, 2, 3]

For this task, a non-differentiable way works perfect:

x = [1, 2, 3, 4,5,6] counts = torch.sum(torch.Tensor(arrival_times)[:, None] < torch.Tensor(x), dim=0) 

It turns out the < operation here is not differentiable. I need a differentiable approximation of this operation.

What I could think of is to subtract the x from arrival_times with broadcasting which leads the following array.

[ [1.1, 0.1, -0.9, -1.9, -2.9, -3.9] [1.9, 0.9, -0.1, -1.1, -2.1, -3.1] [4.1, 3.1, 2.1, 1.1, 0.1, -0.9] ] 

And then somehow count the number of negative (and also zero preferably) elements vertically which will give us the counts [0, 0, 2, 2, 2, 3].

Is there a way to do this or completely new idea for such approximation?

I have an array of time of arrivals and I want to convert it to count data using pytorch in a differentiable way.

Example arrival times:

arrival_times = [2.1, 2.9, 5.1]

and let's say the total range is 6 seconds. What I want to have is:

counts = [0, 0, 2, 2, 2, 3]

For this task, a non-differentiable way works perfect:

x = [1, 2, 3, 4,5,6] counts = torch.sum(arrival_times[:, None] < torch.Tensor(x), dim=1) 

It turns out the < operation here is not differentiable. I need a differentiable approximation of this operation.

What I could think of is to subtract the x from arrival_times with broadcasting which leads the following array.

[ [1.1, 0.1, -0.9, -1.9, -2.9, -3.9] [1.9, 0.9, -0.1, -1.1, -2.1, -3.1] [4.1, 3.1, 2.1, 1.1, 0.1, -0.9] ] 

And then somehow count the number of negative (and also zero preferably) elements vertically which will give us the counts [0, 0, 2, 2, 2, 3].

Is there a way to do this or completely new idea for such approximation?

I have an array of time of arrivals and I want to convert it to count data using pytorch in a differentiable way.

Example arrival times:

arrival_times = [2.1, 2.9, 5.1]

and let's say the total range is 6 seconds. What I want to have is:

counts = [0, 0, 2, 2, 2, 3]

For this task, a non-differentiable way works perfect:

x = [1, 2, 3, 4,5,6] counts = torch.sum(arrival_times[:, None] < torch.Tensor(x), dim=0) 

It turns out the < operation here is not differentiable. I need a differentiable approximation of this operation.

What I could think of is to subtract the x from arrival_times with broadcasting which leads the following array.

[ [1.1, 0.1, -0.9, -1.9, -2.9, -3.9] [1.9, 0.9, -0.1, -1.1, -2.1, -3.1] [4.1, 3.1, 2.1, 1.1, 0.1, -0.9] ] 

And then somehow count the number of negative (and also zero preferably) elements vertically which will give us the counts [0, 0, 2, 2, 2, 3].

Is there a way to do this or completely new idea for such approximation?