Backward pass (loss.backward) in PyTorch - Model Pipeline Trace

Model Pipeline - Backward pass (loss.backward)

This pipeline shows how a simple neural network learns by calculating errors and then updating itself using the backward pass with loss.backward(). This step helps the model improve by adjusting weights based on the error.

Data Flow - 5 Stages

1Data input

1000 rows x 3 columns→Raw input features representing 3 measurements per sample→1000 rows x 3 columns

[[0.5, 1.2, 3.3], [1.1, 0.7, 2.8], ...]

↓

2Forward pass

1000 rows x 3 columns→Input passed through linear layer and activation to produce predictions→1000 rows x 1 column

[[0.7], [0.3], ...]

↓

3Loss calculation

1000 rows x 1 column (predictions) and 1000 rows x 1 column (targets)→Calculate mean squared error between predictions and true values→Scalar loss value

loss = 0.25

↓

4Backward pass

Scalar loss value→Compute gradients of loss with respect to model parameters using loss.backward()→Gradients stored in model parameters

model.weight.grad = tensor([[0.1, -0.05, 0.02]])

↓

5Parameter update

Model parameters and their gradients→Adjust model weights using gradients (e.g., optimizer.step())→Updated model parameters

model.weight updated from tensor([[0.5, 0.3, 0.2]]) to tensor([[0.49, 0.305, 0.198]])

Training Trace - Epoch by Epoch

Loss
0.5 |*****
0.4 |**** 
0.3 |***  
0.2 |**   
0.1 |*    
    +------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.50	0.60	Initial loss is high; accuracy is low as model starts learning
2	0.35	0.72	Loss decreased; accuracy improved after backward pass updates
3	0.25	0.80	Loss continues to decrease; model is learning well
4	0.18	0.85	Loss decreasing steadily; accuracy improving
5	0.12	0.90	Model converging with low loss and high accuracy

Prediction Trace - 5 Layers

Layer 1: Input layer

Layer 2: Linear layer

Layer 3: Activation (ReLU)

Layer 4: Loss calculation

Layer 5: Backward pass (loss.backward())

Model Quiz - 3 Questions

What does the backward pass (loss.backward()) compute?

A Input data normalization

B Final predictions of the model

C Gradients of loss with respect to model parameters

D Loss value calculation

Key Insight

The backward pass is essential for learning. It calculates gradients that tell the model how to adjust its weights to reduce errors. This process repeated over epochs helps the model improve its predictions.

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