Gradient descent optimization in ML Python

Introduction

Gradient descent helps a model learn by slowly improving its guesses to make fewer mistakes.

When training a model to find the best settings that reduce errors.

When you want to improve predictions step by step using data.

When adjusting weights in neural networks to get better results.

When minimizing a function that measures how wrong the model is.

When you want a simple way to optimize many types of models.

Syntax

ML Python

for each step:
    calculate gradient of loss with respect to parameters
    update parameters by moving opposite to gradient scaled by learning rate

The 'gradient' shows the direction to change parameters to reduce error.

The 'learning rate' controls how big each step is; too big can overshoot, too small can be slow.

Examples

This updates the weights by moving them opposite to the gradient scaled by the learning rate.

ML Python

weights = weights - learning_rate * gradient

A simple loop showing repeated updates to weights to reduce loss over 100 steps.

ML Python

for epoch in range(100):
    predictions = model(inputs)
    loss = loss_function(predictions, targets)
    gradient = compute_gradient(loss, weights)
    weights -= learning_rate * gradient

Sample Model

This code fits a line y=2x+1 using gradient descent to find weight and bias that minimize the error.

ML Python

import numpy as np

# Simple linear regression using gradient descent

# Data: y = 2x + 1
x = np.array([1, 2, 3, 4, 5], dtype=float)
y = 2 * x + 1

# Initialize parameters
weight = 0.0
bias = 0.0
learning_rate = 0.1

for epoch in range(20):
    # Predictions
    y_pred = weight * x + bias
    
    # Calculate error
    error = y_pred - y
    
    # Calculate gradients
    dweight = (2/len(x)) * np.dot(error, x)
    dbias = (2/len(x)) * np.sum(error)
    
    # Update parameters
    weight -= learning_rate * dweight
    bias -= learning_rate * dbias
    
    # Calculate loss (mean squared error)
    loss = np.mean(error ** 2)
    print(f"Epoch {epoch+1}: loss={loss:.4f}, weight={weight:.4f}, bias={bias:.4f}")

Important Notes

Choosing the right learning rate is important: too high can make training unstable, too low can make it slow.

Gradient descent can get stuck in flat or bad spots; more advanced methods help avoid this.

Batch gradient descent uses all data each step; stochastic uses one example; mini-batch uses small groups.

Summary

Gradient descent helps models learn by adjusting parameters to reduce errors.

It works by moving parameters opposite to the gradient of the loss.

Small steps controlled by learning rate improve the model gradually.

Practice

1. What is the main goal of gradient descent in machine learning?

easy

A. To minimize the error or loss function

B. To increase the number of model parameters

C. To randomly change model weights

D. To maximize the training time

Solution

1. Step 1: Understand gradient descent purpose

   Gradient descent is used to find the best model parameters by reducing errors.

2. Step 2: Connect to error minimization

   The algorithm updates parameters to minimize the loss function, which measures error.

3. Final Answer:

   To minimize the error or loss function -> Option A

4. Quick Check:

   Goal = minimize loss [OK]

Hint: Gradient descent reduces errors step-by-step [OK]

Common Mistakes:

• Thinking it increases parameters
• Believing it changes weights randomly
• Confusing it with training time increase

2. Which of the following is the correct update rule for a parameter \(\theta\) using gradient descent with learning rate \(\alpha\) and gradient \(\nabla J(\theta)\)?

easy

A. \(\theta = \theta - \alpha \nabla J(\theta)\)

B. \(\theta = \theta + \alpha \nabla J(\theta)\)

C. \(\theta = \alpha \nabla J(\theta) - \theta\)

D. \(\theta = \theta \times \alpha \nabla J(\theta)\)

Solution

1. Step 1: Recall gradient descent formula

   Gradient descent updates parameters by moving opposite to the gradient to reduce loss.

2. Step 2: Identify correct sign and terms

   The update is \(\theta = \theta - \alpha \nabla J(\theta)\), subtracting the gradient scaled by learning rate.

3. Final Answer:

   \(\theta = \theta - \alpha \nabla J(\theta)\) -> Option A

4. Quick Check:

   Update = subtract gradient [OK]

Hint: Subtract gradient times learning rate [OK]

Common Mistakes:

• Adding instead of subtracting gradient
• Multiplying parameters incorrectly
• Swapping terms order

3. Consider this Python code snippet for one step of gradient descent on parameter \(\theta\):

theta = 2.0
learning_rate = 0.1
gradient = 3.0

theta = theta - learning_rate * gradient
print(round(theta, 2))

What will be the printed output?

medium

A. -0.1

B. 1.3

C. 2.3

D. 1.7

Solution

1. Step 1: Calculate the update amount

   Update = learning_rate * gradient = 0.1 * 3.0 = 0.3

2. Step 2: Apply update to theta

   New theta = 2.0 - 0.3 = 1.7

3. Step 3: Check printed value

   Printed value is rounded to 2 decimals: 1.7

4. Final Answer:

   1.7 -> Option D

5. Quick Check:

   2.0 - 0.3 = 1.7 [OK]

Hint: Subtract learning_rate * gradient from theta [OK]

Common Mistakes:

• Adding instead of subtracting update
• Mixing gradient and learning rate
• Rounding incorrectly

4. The following code tries to perform one gradient descent step but has a bug:

theta = 5.0
learning_rate = 0.01
gradient = -4.0

theta = theta + learning_rate * gradient
print(theta)

What is the bug and how to fix it?

medium

A. No bug; code is correct

B. Bug: learning rate too small; fix by increasing it

C. Bug: sign error; fix by changing '+' to '-' in update

D. Bug: gradient sign wrong; fix by negating gradient

Solution

1. Step 1: Recall standard gradient descent formula

   The correct update is always \(\theta = \theta - \alpha \nabla J(\theta)\).

2. Step 2: Identify the bug in code

   The code uses '+' instead of '-', performing gradient ascent. With gradient = -4.0, code updates to 5.0 - 0.04 = 4.96 (wrong direction); correct is 5.0 + 0.04 = 5.04.

3. Final Answer:

   Bug: sign error; fix by changing '+' to '-' in update -> Option C

4. Quick Check:

   Always subtract lr * gradient [OK]

Hint: Always use '-' for gradient descent [OK]

Common Mistakes:

• Thinking '+' works for negative gradients
• Confusing ascent (+) with descent (-)
• Ignoring standard update rule

5. You run gradient descent with a very large learning rate \(\alpha = 10\) on a simple quadratic loss \(J(\theta) = (\theta - 3)^2\). What is the most likely outcome after a few steps starting from \(\theta=0\)?

hard

A. The parameter \(\theta\) converges smoothly to 3

B. The parameter \(\theta\) oscillates or diverges away from 3

C. The parameter \(\theta\) stays at 0 without change

D. The parameter \(\theta\) becomes negative infinity

Solution

1. Step 1: Understand effect of large learning rate

   A large learning rate causes big jumps in parameter updates, possibly overshooting the minimum.

2. Step 2: Analyze behavior on quadratic loss

   Since \(J(\theta) = (\theta - 3)^2\), gradient is \(2(\theta - 3)\). Large steps can cause \(\theta\) to jump past 3 repeatedly, causing oscillation or divergence.

3. Final Answer:

   The parameter \(\theta\) oscillates or diverges away from 3 -> Option B

4. Quick Check:

   Large learning rate causes oscillation [OK]

Hint: Too big steps cause oscillation, not smooth learning [OK]

Common Mistakes:

• Assuming large learning rate helps convergence
• Thinking parameter stays fixed
• Confusing divergence with negative infinity