CosineAnnealingLR in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of the CosineAnnealingLR scheduler in PyTorch?

CosineAnnealingLR adjusts the learning rate following a cosine curve, gradually decreasing it to a minimum value to help the model converge better during training.

beginner

How does the learning rate change over time with CosineAnnealingLR?

The learning rate starts at the initial value and decreases following a half cosine wave until it reaches the minimum learning rate at the end of the cycle.

intermediate

What are the key parameters of CosineAnnealingLR in PyTorch?

The key parameters are 'optimizer' (the optimizer to adjust), 'T_max' (the number of iterations for one cycle), and 'eta_min' (the minimum learning rate).

intermediate

Why might you choose CosineAnnealingLR over a constant learning rate?

Because it helps the model avoid getting stuck in bad local minima by reducing the learning rate smoothly, which can improve training stability and final accuracy.

beginner

Show a simple PyTorch code snippet to create a CosineAnnealingLR scheduler.

import torch.optim as optim

optimizer = optim.SGD(model.parameters(), lr=0.1)
scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10, eta_min=0.001)

for epoch in range(10):
    train()
    scheduler.step()

What does the 'T_max' parameter in CosineAnnealingLR represent?

A The number of iterations for one cosine cycle

B The maximum learning rate

C The minimum learning rate

D The optimizer type

'T_max' sets how many iterations or epochs the scheduler takes to complete one cosine annealing cycle.

What happens to the learning rate at the end of the CosineAnnealingLR cycle?

A It increases exponentially

B It becomes zero

C It resets to the initial learning rate

D It reaches the minimum learning rate 'eta_min'

At the end of the cycle, the learning rate reaches the minimum value specified by 'eta_min'.

Which optimizer can CosineAnnealingLR be used with?

A Any PyTorch optimizer

B Only Adam

C Only RMSprop

D Only SGD

CosineAnnealingLR works with any PyTorch optimizer passed to it.

Why is cosine annealing beneficial for training neural networks?

A It keeps the learning rate constant

B It smoothly decreases the learning rate to avoid sharp drops

C It increases the learning rate over time

D It randomly changes the learning rate

Cosine annealing smoothly decreases the learning rate, helping training stability and convergence.

What is the default value of 'eta_min' in CosineAnnealingLR if not specified?

A 0.1

B 0.001

C 0.0

D 1.0

By default, 'eta_min' is 0.0, meaning the learning rate can anneal down to zero.

Explain how the CosineAnnealingLR scheduler adjusts the learning rate during training.

Think about how the learning rate changes smoothly over time.

Describe a simple PyTorch training loop using CosineAnnealingLR.

Focus on where the scheduler fits in the training process.

Practice

1. What is the main purpose of using CosineAnnealingLR in PyTorch training?

easy

A. To stop training early when accuracy is high

B. To increase the batch size during training

C. To smoothly adjust the learning rate in a wave-like pattern

D. To shuffle the training data every epoch

Solution

1. Step 1: Understand the role of learning rate schedulers

   Learning rate schedulers adjust the learning rate during training to improve convergence.

2. Step 2: Identify what CosineAnnealingLR does

   CosineAnnealingLR changes the learning rate smoothly following a cosine curve, avoiding sudden jumps.

3. Final Answer:

   To smoothly adjust the learning rate in a wave-like pattern -> Option C

4. Quick Check:

   CosineAnnealingLR = smooth wave learning rate [OK]

Hint: CosineAnnealingLR changes learning rate smoothly like a wave [OK]

Common Mistakes:

• Thinking it changes batch size
• Confusing it with early stopping
• Assuming it shuffles data

2. Which of the following is the correct way to create a CosineAnnealingLR scheduler in PyTorch with a cycle length of 10 epochs and minimum learning rate 0.001?

easy

A. scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10, eta_min=0.001)

B. scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, max_T=10, min_lr=0.001)

C. scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)

D. scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10, min_lr=0.001)

Solution

1. Step 1: Check the official PyTorch parameter names

   The correct parameters are T_max for cycle length and eta_min for minimum learning rate.

2. Step 2: Match parameters with options

   scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10, eta_min=0.001) uses T_max=10 and eta_min=0.001, which is correct syntax.

3. Final Answer:

   scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10, eta_min=0.001) -> Option A

4. Quick Check:

   Use T_max and eta_min parameters [OK]

Hint: Use T_max and eta_min exactly as parameter names [OK]

Common Mistakes:

• Using wrong parameter names like max_T or min_lr
• Omitting eta_min when needed
• Swapping parameter order incorrectly

3. Given the code below, what will be the learning rate after 5 calls to scheduler.step() if initial lr is 0.1, T_max=10, and eta_min=0?

optimizer = torch.optim.SGD(model.parameters(), lr=0.1)
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10, eta_min=0)
for _ in range(5):
    scheduler.step()
print(optimizer.param_groups[0]['lr'])

medium

A. 0.0

B. Approximately 0.0707

C. 0.1

D. 0.05

Solution

1. Step 1: Understand CosineAnnealingLR formula

   Learning rate after t calls to step() is: eta_min + 0.5*(initial_lr - eta_min)*(1 + cos(pi * t / T_max))

2. Step 2: Calculate learning rate at t=5

   lr = 0 + 0.5*0.1*(1 + cos(pi*5/10)) = 0.05*(1 + cos(pi/2)) = 0.05*(1 + 0) = 0.05 exactly.

3. Final Answer:

   0.05 -> Option D

4. Quick Check:

   Cosine formula at step 5 = 0.05 [OK]

Hint: Use cosine formula: lr = eta_min + 0.5*(lr0 - eta_min)*(1+cos(pi*t/T_max)) at t=5 = 0.05 [OK]

Common Mistakes:

• Assuming lr stays constant
• Confusing step count indexing
• Ignoring eta_min in calculation
• Miscalculating to ~0.0707

4. Identify the error in the following code snippet using CosineAnnealingLR:

optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=5)
for epoch in range(10):
    train()
    scheduler.step()

medium

A. scheduler.step() should be called before train()

B. No error, code is correct

C. T_max should be equal to total epochs (10) not 5

D. Learning rate should be set to 0.1 for Adam optimizer

Solution

1. Step 1: Understand scheduler.step() timing

   Standard PyTorch practice is to call scheduler.step() after train() to update LR for the next epoch.

2. Step 2: Verify the code

   The loop trains with current LR then steps, which is correct. T_max=5 works for 10 epochs as the schedule continues.

3. Final Answer:

   No error, code is correct -> Option B

4. Quick Check:

   train() then scheduler.step() [OK]

Hint: Call scheduler.step() after train() [OK]

Common Mistakes:

• Thinking step() goes before train()
• Requiring T_max = total epochs
• Dictating specific LR for Adam

5. You want to train a model for 50 epochs using CosineAnnealingLR with 2 cycles of learning rate decay. How should you set T_max and why?

hard

A. Set T_max=25 to have two full cosine cycles over 50 epochs

B. Set T_max=50 to have one full cosine cycle over 50 epochs

C. Set T_max=100 to have half a cosine cycle over 50 epochs

D. Set T_max=10 to have five full cosine cycles over 50 epochs

Solution

1. Step 1: Understand T_max meaning

   T_max is the number of epochs for one full cosine cycle of learning rate decay.

2. Step 2: Calculate T_max for 2 cycles in 50 epochs

   To have 2 cycles in 50 epochs, each cycle should last 25 epochs, so T_max=25.

3. Final Answer:

   Set T_max=25 to have two full cosine cycles over 50 epochs -> Option A

4. Quick Check:

   Two cycles = total epochs / 2 = 25 [OK]

Hint: Divide total epochs by number of cycles for T_max [OK]

Common Mistakes:

• Setting T_max equal to total epochs for multiple cycles
• Confusing half and full cycles
• Choosing T_max larger than total epochs