Optimizers (SGD, Adam) in PyTorch

Introduction

Optimizers help a machine learning model learn by adjusting its settings to make better guesses.

When training a model to recognize images or sounds.

When you want the model to improve its predictions step by step.

When you need to find the best settings for your model automatically.

When comparing different ways to teach a model to see which works faster.

When fine-tuning a model to get more accurate results.

Syntax

PyTorch

optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
# or
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

SGD stands for Stochastic Gradient Descent, a simple way to update model settings.

Adam is a smarter optimizer that adapts learning rates for each setting automatically.

Examples

Creates an SGD optimizer with a learning rate of 0.1.

PyTorch

optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

Creates an Adam optimizer with a learning rate of 0.001.

PyTorch

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

SGD optimizer with momentum to help speed up learning.

PyTorch

optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)

Sample Model

This code trains a simple model to learn the rule y = 2x + 1 using SGD optimizer. It prints loss each step and shows prediction for input 5.

PyTorch

import torch
import torch.nn as nn
import torch.optim as optim

# Simple model: one linear layer
model = nn.Linear(1, 1)

# Data: y = 2x + 1
x = torch.tensor([[1.0], [2.0], [3.0], [4.0]])
y = torch.tensor([[3.0], [5.0], [7.0], [9.0]])

# Choose optimizer: SGD or Adam
optimizer = optim.SGD(model.parameters(), lr=0.1)
# optimizer = optim.Adam(model.parameters(), lr=0.1)

# Loss function
criterion = nn.MSELoss()

# Training loop
for epoch in range(10):
    optimizer.zero_grad()  # Clear old gradients
    outputs = model(x)     # Predict
    loss = criterion(outputs, y)  # Calculate loss
    loss.backward()       # Calculate gradients
    optimizer.step()      # Update model
    print(f"Epoch {epoch+1}, Loss: {loss.item():.4f}")

# Final prediction
test_input = torch.tensor([[5.0]])
prediction = model(test_input).item()
print(f"Prediction for input 5: {prediction:.2f}")

Important Notes

SGD is simple and works well for many problems but may need tuning of learning rate.

Adam often works better without much tuning because it adjusts learning rates automatically.

Always clear gradients with optimizer.zero_grad() before backpropagation.

Summary

Optimizers help models learn by updating their settings to reduce mistakes.

SGD is a basic optimizer; Adam is more advanced and adapts learning rates.

Choosing the right optimizer and learning rate affects how fast and well your model learns.

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