Optimizers (SGD, Adam) in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main role of an optimizer in training a neural network?

An optimizer updates the model's weights to reduce the difference between predictions and true values, helping the model learn from data.

beginner

What does SGD stand for and how does it update weights?

SGD stands for Stochastic Gradient Descent. It updates weights by moving them a small step opposite to the gradient of the loss, using a fixed learning rate.

intermediate

How does Adam optimizer differ from SGD?

Adam combines ideas from momentum and adaptive learning rates. It adjusts learning rates for each weight individually using estimates of first and second moments of gradients.

intermediate

What are the key hyperparameters of Adam optimizer?

The key hyperparameters are learning rate, beta1 (momentum decay), beta2 (RMS decay), and epsilon (small number to avoid division by zero).

intermediate

Why might you choose Adam over SGD for training a model?

Adam often converges faster and requires less tuning of learning rate because it adapts learning rates per parameter and uses momentum, making it good for complex or noisy problems.

What does SGD use to update model weights?

A Gradient of loss and fixed learning rate

B Random weight changes

C Second moment estimates

D Adaptive learning rates per weight

SGD updates weights by moving opposite to the gradient of the loss using a fixed learning rate.

Which optimizer adapts learning rates for each parameter individually?

A SGD

B Gradient Descent

C Adam

D RMSProp

Adam adapts learning rates per parameter using estimates of first and second moments of gradients.

What is the purpose of the beta1 parameter in Adam optimizer?

A Controls learning rate

B Controls momentum decay

C Prevents division by zero

D Controls batch size

Beta1 controls the decay rate of the moving average of past gradients, acting like momentum.

Which optimizer is generally better for noisy or complex problems?

A None

B SGD

C Vanilla Gradient Descent

D Adam

Adam adapts learning rates and uses momentum, making it better for noisy or complex problems.

What does the epsilon parameter in Adam do?

A Avoids division by zero

B Controls momentum

C Sets learning rate

D Adjusts batch size

Epsilon is a small number added to prevent division by zero during calculations.

Explain how SGD updates model weights during training.

Think about moving weights opposite to the slope of the loss.

Describe the advantages of using Adam optimizer compared to SGD.

Consider how Adam adjusts learning rates and remembers past gradients.

Practice

1. Which optimizer in PyTorch adapts the learning rate for each parameter automatically?

easy

A. Adam

B. SGD

C. RMSprop

D. Adagrad

Solution

1. Step 1: Understand optimizer behavior

   Adam optimizer adjusts learning rates for each parameter based on past gradients.

2. Step 2: Compare with SGD

   SGD uses a fixed learning rate for all parameters without adaptation.

3. Final Answer:

   Adam -> Option A

4. Quick Check:

   Adaptive learning rate = Adam [OK]

Hint: Adam adapts learning rates per parameter automatically [OK]

Common Mistakes:

• Confusing SGD as adaptive optimizer
• Thinking RMSprop is the only adaptive optimizer
• Assuming Adagrad is default in PyTorch

2. Which of the following is the correct way to create an SGD optimizer in PyTorch with learning rate 0.01?

easy

A. optimizer = torch.optim.SGD(model, lr=0.01)

B. optimizer = torch.SGD(model.parameters(), learning_rate=0.01)

C. optimizer = torch.optim.Adam(model.parameters(), lr=0.01)

D. optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

Solution

1. Step 1: Check PyTorch optimizer syntax

   Correct syntax uses torch.optim.SGD with model.parameters() and lr argument.

2. Step 2: Identify errors in other options

   The option with torch.SGD(model.parameters(), learning_rate=0.01) uses wrong module and argument name; the option with Adam uses wrong optimizer; the option passing model instead of parameters is incorrect.

3. Final Answer:

   optimizer = torch.optim.SGD(model.parameters(), lr=0.01) -> Option D

4. Quick Check:

   Correct syntax = optimizer = torch.optim.SGD(model.parameters(), lr=0.01) [OK]

Hint: Use torch.optim.SGD with model.parameters() and lr= value [OK]

Common Mistakes:

• Passing model instead of model.parameters()
• Using wrong argument name like learning_rate
• Confusing Adam with SGD

3. What will be the output loss value after one step of training with this code snippet?

import torch
import torch.nn as nn
model = nn.Linear(2, 1)
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)
criterion = nn.MSELoss()

inputs = torch.tensor([[1.0, 2.0]])
target = torch.tensor([[1.0]])

optimizer.zero_grad()
output = model(inputs)
loss = criterion(output, target)
loss.backward()
optimizer.step()

print(round(loss.item(), 3))

medium

A. 0.5

B. 0.25

C. Cannot determine exact value

D. 0.75

Solution

1. Step 1: Understand loss calculation

   Loss depends on random initial weights of model, so exact value varies each run.

2. Step 2: Check code behavior

   Since weights are random, output and loss are not fixed; cannot predict exact loss value.

3. Final Answer:

   Cannot determine exact value -> Option C

4. Quick Check:

   Random init means loss unknown [OK]

Hint: Random weights mean loss value varies; exact output unknown [OK]

Common Mistakes:

• Assuming fixed loss value without checking randomness
• Ignoring model initialization effect
• Confusing loss before and after optimizer step

4. Identify the error in this PyTorch optimizer setup code:

optimizer = torch.optim.Adam(model.parameters, lr=0.001)

medium

A. Adam optimizer does not accept learning rate argument

B. model.parameters should be called as model.parameters()

C. optimizer should be torch.SGD not Adam

D. lr value should be an integer, not float

Solution

1. Step 1: Check method usage

   model.parameters is a method and must be called with parentheses to get parameters.

2. Step 2: Validate other options

   Adam accepts lr argument; SGD is not mandatory; lr can be float.

3. Final Answer:

   model.parameters should be called as model.parameters() -> Option B

4. Quick Check:

   Call parameters() method correctly [OK]

Hint: Always call model.parameters() with parentheses [OK]

Common Mistakes:

• Forgetting parentheses on model.parameters
• Thinking Adam can't take lr argument
• Assuming lr must be integer

5. You want to train a model that converges quickly on noisy data. Which optimizer and learning rate combination is generally best to start with?

hard

A. Adam with lr=0.001

B. SGD with lr=0.1

C. SGD with lr=0.0001

D. Adam with lr=0.1

Solution

1. Step 1: Consider optimizer suitability for noisy data

   Adam adapts learning rates and handles noisy gradients better than SGD.

2. Step 2: Choose appropriate learning rate

   Typical starting lr for Adam is 0.001; too high (0.1) can cause instability.

3. Final Answer:

   Adam with lr=0.001 -> Option A

4. Quick Check:

   Adaptive optimizer + moderate lr = Adam 0.001 [OK]

Hint: Use Adam with 0.001 lr for noisy data to converge fast [OK]

Common Mistakes:

• Using too high learning rate with Adam
• Choosing SGD for noisy data without adaptation
• Confusing learning rate scales