ReduceLROnPlateau in PyTorch

Introduction

ReduceLROnPlateau helps your model learn better by lowering the learning speed when progress slows down.

When your model's training loss stops improving for a few steps.

When validation accuracy stays the same for several checks.

When you want to avoid wasting time with a learning rate that is too high.

When you want to automatically adjust learning rate without manual tuning.

Syntax

PyTorch

torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=0.1, patience=10, verbose=False, threshold=1e-4, threshold_mode='rel', cooldown=0, min_lr=0, eps=1e-8)

mode='min' means the scheduler looks for the metric to decrease (like loss).

factor is how much to reduce the learning rate (e.g., 0.1 means reduce by 10 times).

Examples

Reduces learning rate by half if loss does not improve for 5 checks.

PyTorch

scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=0.5, patience=5)

Reduces learning rate by 10 times if accuracy does not improve for 3 checks.

PyTorch

scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', factor=0.1, patience=3)

Sample Model

This example shows how ReduceLROnPlateau lowers the learning rate when the loss stops improving for 2 epochs.

PyTorch

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

# Simple model
model = nn.Linear(10, 1)

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

# Scheduler to reduce LR when loss plateaus
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=0.5, patience=2, verbose=True)

# Dummy data
inputs = torch.randn(5, 10)
targets = torch.randn(5, 1)

criterion = nn.MSELoss()

losses = [0.5, 0.4, 0.4, 0.4, 0.3, 0.3, 0.3]

for epoch, loss_val in enumerate(losses, 1):
    optimizer.zero_grad()
    outputs = model(inputs)
    loss = criterion(outputs, targets)
    loss.backward()
    optimizer.step()

    # Instead of real loss, we simulate loss_val to test scheduler
    scheduler.step(loss_val)
    print(f"Epoch {epoch}, Loss: {loss_val}, Learning Rate: {optimizer.param_groups[0]['lr']}")

Important Notes

Remember to call scheduler.step(metric) with the metric you want to monitor (like validation loss).

Verbose=True helps you see when the learning rate changes.

Patience controls how many checks to wait before reducing the learning rate.

Summary

ReduceLROnPlateau lowers learning rate when progress stops.

It helps models learn better by adjusting speed automatically.

Use it by giving the metric to monitor after each epoch.

Practice

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

easy

A. To shuffle the training data before each epoch

B. To increase the batch size automatically during training

C. To stop training early when accuracy reaches a threshold

D. To reduce the learning rate when a monitored metric stops improving

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 ReduceLROnPlateau does

   This scheduler reduces the learning rate when a monitored metric (like validation loss) stops improving.

3. Final Answer:

   To reduce the learning rate when a monitored metric stops improving -> Option D

4. Quick Check:

   ReduceLROnPlateau lowers LR on no improvement [OK]

Hint: Remember: it lowers LR when progress stalls [OK]

Common Mistakes:

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

2. Which of the following is the correct way to create a ReduceLROnPlateau scheduler in PyTorch?

easy

A. scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min')

B. scheduler = torch.optim.ReduceLROnPlateau(optimizer, mode='max')

C. scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10)

D. scheduler = torch.optim.ReduceLROnPlateau(optimizer, patience=5)

Solution

1. Step 1: Check the correct module and class name

   The correct class is ReduceLROnPlateau inside torch.optim.lr_scheduler.

2. Step 2: Verify the constructor parameters

   It requires the optimizer and optional parameters like mode. scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min') uses correct syntax and parameters.

3. Final Answer:

   scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min') -> Option A

4. Quick Check:

   Correct class and module usage [OK]

Hint: Use torch.optim.lr_scheduler.ReduceLROnPlateau with optimizer [OK]

Common Mistakes:

• Using wrong module path
• Confusing with StepLR scheduler
• Missing required optimizer argument

3. Given the code below, what will be the learning rate after the third call to scheduler.step(val_loss) if val_loss values are [0.5, 0.4, 0.4, 0.4] and patience=2?

optimizer = torch.optim.SGD(model.parameters(), lr=0.1)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', patience=2, factor=0.1)

val_losses = [0.5, 0.4, 0.4, 0.4]
for loss in val_losses:
    scheduler.step(loss)
    print(f"LR: {optimizer.param_groups[0]['lr']}")

medium

A. 0.1

B. 0.01

C. 0.001

D. 0.4

Solution

1. Step 1: Understand patience and when LR reduces

   Patience=2 means LR reduces after 2 epochs with no improvement in monitored metric.

2. Step 2: Analyze val_loss sequence and scheduler calls

   val_loss improves from 0.5 to 0.4 at second call, then stays same (no improvement) for next two calls. LR reduces only after 2 consecutive no improvements, so after the fourth call, not the third.

3. Final Answer:

   0.1 -> Option A

4. Quick Check:

   LR reduces after patience epochs, not before [OK]

Hint: LR changes after patience epochs without improvement [OK]

Common Mistakes:

• Reducing LR immediately on no improvement
• Confusing patience count
• Using val_loss value as LR

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

optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer)

for epoch in range(5):
    train()
    val_loss = validate()
    scheduler.step()

medium

A. Learning rate must be set to 0.1 initially

B. Optimizer should be SGD, not Adam

C. Missing metric argument in scheduler.step() call

D. scheduler.step() should be called before training

Solution

1. Step 1: Check how ReduceLROnPlateau.step() is called

   This scheduler requires the monitored metric (e.g., val_loss) as an argument in step().

2. Step 2: Identify missing argument in code

   The code calls scheduler.step() without passing val_loss, causing an error.

3. Final Answer:

   Missing metric argument in scheduler.step() call -> Option C

4. Quick Check:

   Pass metric to step() for ReduceLROnPlateau [OK]

Hint: Always pass metric to scheduler.step() for ReduceLROnPlateau [OK]

Common Mistakes:

• Calling step() without metric
• Confusing optimizer type
• Wrong order of scheduler call

5. You want to train a model and reduce the learning rate by half if the validation accuracy does not improve for 3 epochs. Which of the following is the correct way to set up ReduceLROnPlateau for this task?

hard

A. scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', factor=2.0, patience=3)

B. scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', factor=0.5, patience=3)

C. scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=0.5, patience=3)

D. scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=2.0, patience=3)

Solution

1. Step 1: Determine the mode based on metric type

   Validation accuracy should be maximized, so mode='max' is correct.

2. Step 2: Set factor and patience correctly

   Factor=0.5 halves the learning rate, patience=3 waits 3 epochs before reducing.

3. Final Answer:

   scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', factor=0.5, patience=3) -> Option B

4. Quick Check:

   Maximize accuracy, reduce LR by half after 3 no improvements [OK]

Hint: Use mode='max' for accuracy, factor <1 to reduce LR [OK]

Common Mistakes:

• Using mode='min' for accuracy
• Setting factor > 1 (increases LR)
• Confusing patience value