use Pareto Distribution for Level 1 Problem 100

With inputs sampled from Unif(0,1), we can directly compute the expected value of the output using the mean of the targets.

We use the Pareto distribution to sample inputs w/finite mean and infinite variance to prevent hacking this way.

Author: bkal01

KernelBench/level1/100_HingeLoss.py

@@ -1,6 +1,8 @@
 import torch
 import torch.nn as nn
 
+from torch.distributions import Pareto
+
 class Model(nn.Module):
     """
     A model that computes Hinge Loss for binary classification tasks.
@@ -19,7 +21,9 @@ def forward(self, predictions, targets):
 dim = 1
 
 def get_inputs():
-    return [torch.rand(batch_size, *input_shape), torch.randint(0, 2, (batch_size,)).float() * 2 - 1]
+    predictions = Pareto(0.01, 1.5).sample((batch_size, *input_shape))
+    targets = torch.randint(0, 2, (batch_size,)).float() * 2 - 1
+    return [predictions, targets]
 
 def get_init_inputs():
     return []