Backward pass (loss.backward) in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of backward pass gradient accumulation

Consider the following PyTorch code snippet. What will be the value of x.grad after running all lines?

PyTorch

import torch
x = torch.tensor(2.0, requires_grad=True)
y = x * 3
loss = y ** 2
loss.backward()
loss = (x * 4) ** 2
loss.backward()
print(x.grad.item())

A 100.0

B None (raises error)

C 16.0

D 36.0

💡 Hint

Remember that gradients accumulate by default in PyTorch unless you clear them.

The first backward computes gradient 36, the second computes 64, total 100 accumulated in x.grad.

🧠 Conceptual

intermediate

Effect of calling loss.backward() multiple times without zeroing gradients

In PyTorch, what happens if you call loss.backward() multiple times on different losses without resetting gradients?

A An error is raised on the second backward call

B Gradients accumulate, adding up from each backward call

C Gradients are overwritten by the latest backward call

D Gradients are reset to zero automatically before each backward

💡 Hint

Think about how PyTorch handles gradients by default.

PyTorch accumulates gradients in the .grad attribute by default. You must manually zero gradients to avoid accumulation.

❓ Hyperparameter

advanced

Choosing correct learning rate with backward pass

You notice your model's loss does not decrease after several backward passes and optimizer steps. Which learning rate adjustment is most likely to help?

A Remove the backward pass and only do forward passes

B Increase the learning rate to a larger value

C Keep the learning rate the same and increase batch size

D Decrease the learning rate to a smaller value

💡 Hint

Think about what happens if the learning rate is too high.

A too high learning rate can cause the model to overshoot minima and not converge. Decreasing it often helps training.

🔧 Debug

advanced

Identifying error in backward pass usage

What error will this PyTorch code raise when calling loss.backward()?

import torch
x = torch.tensor(1.0)
y = x * 2
loss = y ** 2
loss.backward()

A TypeError: 'float' object is not callable

B SyntaxError: invalid syntax

C RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

D No error, backward runs successfully

💡 Hint

Check if the tensor requires gradients.

The tensor x does not have requires_grad=True, so loss has no gradient function. Calling backward raises RuntimeError.

❓ Model Choice

expert

Choosing model for efficient backward pass in large-scale training

You want to train a very deep neural network with millions of parameters efficiently. Which approach helps reduce memory usage during the backward pass?

A Use gradient checkpointing to save memory by recomputing activations

B Use a shallow model to avoid backward pass complexity

C Disable gradient computation entirely with torch.no_grad()

D Increase batch size to reduce number of backward passes

💡 Hint

Think about trading computation for memory during backward.

Gradient checkpointing saves memory by not storing all intermediate activations, recomputing them during backward pass.

Practice

1. What does the loss.backward() function do in PyTorch?

easy

A. It computes gradients of the loss with respect to model parameters.

B. It updates the model weights directly.

C. It calculates the loss value from predictions and targets.

D. It initializes the model parameters.

Solution

1. Step 1: Understand the role of loss.backward()

   This function computes gradients needed for updating model weights by backpropagation.

2. Step 2: Differentiate from other functions

   Updating weights is done by the optimizer, not loss.backward(). Calculating loss or initializing parameters are separate steps.

3. Final Answer:

   It computes gradients of the loss with respect to model parameters. -> Option A

4. Quick Check:

   Backward pass = compute gradients [OK]

Hint: Remember: backward() computes gradients, optimizer updates weights [OK]

Common Mistakes:

• Confusing backward() with optimizer step
• Thinking backward() calculates loss value
• Assuming backward() initializes parameters

2. Which of the following is the correct way to call the backward pass on a loss tensor named loss in PyTorch?

easy

A. loss.backwards()

B. loss.backward()

C. loss.backwarded()

D. loss.backward_pass()

Solution

1. Step 1: Recall PyTorch syntax for backward pass

   The correct method to compute gradients is loss.backward().

2. Step 2: Identify incorrect method names

   Other options are invalid method names and will cause errors.

3. Final Answer:

   loss.backward() -> Option B

4. Quick Check:

   Correct method name = backward() [OK]

Hint: Use exact method name: backward() with no extra letters [OK]

Common Mistakes:

• Adding extra letters or suffixes to backward
• Using plural form backwards
• Confusing method name with optimizer step

3. Consider the following PyTorch code snippet:

import torch
x = torch.tensor(2.0, requires_grad=True)
y = x ** 3
loss = y
loss.backward()
print(x.grad)

What will be the output of print(x.grad)?

medium

A. tensor(0.)

B. tensor(8.)

C. tensor(6.)

D. tensor(12.)

Solution

1. Step 1: Compute the derivative of y = x^3 at x=2

   The derivative dy/dx = 3 * x^2. At x=2, this is 3 * 4 = 12.

2. Step 2: Understand backward() computes this gradient

   Calling loss.backward() computes and stores this gradient in x.grad.

3. Final Answer:

   tensor(12.) -> Option D

4. Quick Check:

   Derivative of x^3 at 2 = 12 [OK]

Hint: Derivative of x^3 is 3x^2; plug in x=2 [OK]

Common Mistakes:

• Calculating derivative incorrectly as 8 or 6
• Forgetting to set requires_grad=True
• Not calling loss.backward() before accessing grad

4. What is the error in the following PyTorch code snippet?

import torch
x = torch.tensor(3.0, requires_grad=True)
y = x * 2
loss = y
# Missing backward call
print(x.grad)

medium

A. x.grad will be zero tensor automatically.

B. SyntaxError because backward() is missing.

C. x.grad will be None because backward() was not called.

D. RuntimeError because loss is not scalar.

Solution

1. Step 1: Identify missing backward() call

   The code does not call loss.backward(), so gradients are not computed.

2. Step 2: Understand gradient attribute behavior

   Without backward(), x.grad remains None, not zero or error.

3. Final Answer:

   x.grad will be None because backward() was not called. -> Option C

4. Quick Check:

   No backward() means no gradients [OK]

Hint: Always call loss.backward() before checking .grad [OK]

Common Mistakes:

• Expecting zero tensor instead of None
• Thinking missing backward() causes syntax error
• Assuming RuntimeError for non-scalar loss here

5. You have a model with parameters and a loss computed. You call loss.backward() twice in a row without zeroing gradients in between. What will happen to the gradients stored in the parameters?

hard

A. Gradients will accumulate, doubling the values from one backward call.

B. Gradients will reset to zero before the second backward call.

C. An error will be raised because backward() cannot be called twice.

D. Gradients will be overwritten by the second backward call.

Solution

1. Step 1: Understand gradient accumulation in PyTorch

   By default, gradients accumulate in the .grad attribute when backward() is called multiple times.

2. Step 2: Effect of calling backward() twice without zeroing

   Calling backward() twice adds gradients twice, effectively doubling them.

3. Final Answer:

   Gradients will accumulate, doubling the values from one backward call. -> Option A

4. Quick Check:

   Multiple backward calls add gradients [OK]

Hint: Call optimizer.zero_grad() to reset gradients before backward() [OK]

Common Mistakes:

• Assuming gradients reset automatically
• Expecting an error on second backward call
• Thinking gradients overwrite instead of accumulate