Optimizers (SGD, Adam) in PyTorch - Model Pipeline Trace

Model Pipeline - Optimizers (SGD, Adam)

This pipeline shows how two popular optimizers, SGD and Adam, help a simple neural network learn from data by adjusting its weights to reduce errors.

Data Flow - 5 Stages

1Data Input

1000 rows x 10 columns→Raw dataset with 10 features per sample→1000 rows x 10 columns

[0.5, 1.2, 0.3, ..., 0.7]

↓

2Preprocessing

1000 rows x 10 columns→Normalize features to range 0-1→1000 rows x 10 columns

[0.25, 0.6, 0.15, ..., 0.35]

↓

3Model Input Layer

1000 rows x 10 columns→Feed features into neural network input→1000 rows x 10 neurons

[0.25, 0.6, 0.15, ..., 0.35]

↓

4Hidden Layer

1000 rows x 10 neurons→Apply linear transformation and ReLU activation→1000 rows x 5 neurons

[0.0, 0.8, 0.3, 0.0, 0.5]

↓

5Output Layer

1000 rows x 5 neurons→Apply linear transformation to get predictions→1000 rows x 1 column

[0.7, 0.2, 0.9, ..., 0.4]

Training Trace - Epoch by Epoch

Loss
1.0 | *
0.9 | *
0.8 | *
0.7 |  *
0.6 |   *
0.5 |    *
0.4 |     *
0.3 |      *
    +------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.55	Initial training with high loss and low accuracy
2	0.65	0.68	Loss decreased, accuracy improved
3	0.50	0.75	Model learning well, loss dropping steadily
4	0.40	0.82	Good convergence, accuracy increasing
5	0.35	0.85	Training stabilizing with low loss and high accuracy

Prediction Trace - 3 Layers

Layer 1: Input Layer

Layer 2: Hidden Layer (Linear + ReLU)

Layer 3: Output Layer (Linear)

Model Quiz - 3 Questions

What is the main role of the optimizer in training?

A Adjust model weights to reduce error

B Increase the size of the dataset

C Change the input data format

D Visualize the training progress

Key Insight

Optimizers like SGD and Adam guide the model to learn by adjusting weights to reduce errors. Adam often converges faster by adapting learning rates, helping the model improve accuracy steadily over training.

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