Skip to main content

Difference between Batch Gradient Descent and Stochastic Gradient Descent



Gradient Descent
Gradient Descent is a generic optimization algorithm capable of finding optimal solutions to a wide range of problems.
The general idea is to tweak parameters iteratively in order to minimize the cost function.
An important parameter of Gradient Descent (GD) is the size of the steps, determined by the learning rate hyperparameters.
If the learning rate is too small, then the algorithm will have to go through many iterations to converge, which will take a long time, and if it is too high we may jump the optimal value.

Note: When using Gradient Descent, we should ensure that all features have a similar scale (e.g. using Scikit-Learn’s StandardScaler class), or else it will take much longer to converge.

Types of Gradient Descent:

Typically, there are three types of Gradient Descent: 
Batch Gradient Descent
Stochastic Gradient Descent
Mini-batch Gradient Descent

Stochastic Gradient Descent (SGD):

The word ‘stochastic‘ means a system or process linked with a random probability. Hence, in Stochastic Gradient Descent, a few samples are selected randomly instead of the whole data set for each iteration. In Gradient Descent, there is a term called “batch” which denotes the total number of samples from a dataset that is used for calculating the gradient for each iteration. In typical Gradient Descent optimization, like Batch Gradient Descent, the batch is taken to be the whole dataset. Although using the whole dataset is really useful for getting to the minima in a less noisy and less random manner, the problem arises when our dataset gets big.
Suppose, you have a million samples in your dataset, so if you use a typical Gradient Descent optimization technique, you will have to use all of the one million samples for completing one iteration while performing the Gradient Descent, and it has to be done for every iteration until the minima are reached. Hence, it becomes computationally very expensive to perform.
This problem is solved by Stochastic Gradient Descent. In SGD, it uses only a single sample, i.e., a batch size of one, to perform each iteration. The sample is randomly shuffled and selected for performing the iteration.
SGD algorithm:

So, in SGD, we find out the gradient of the cost function of a single example at each iteration instead of the sum of the gradient of the cost function of all the examples.

In SGD, since only one sample from the dataset is chosen at random for each iteration, the path taken by the algorithm to reach the minima is usually noisier than your typical Gradient Descent algorithm. But that doesn’t matter all that much because the path taken by the algorithm does not matter, as long as we reach the minima and with a significantly shorter training time.

The path is taken by Batch Gradient Descent as shown below as follows:
gd_path

A path has been taken by Stochastic Gradient Descent –

sgd_path

One thing to be noted is that, as SGD is generally noisier than typical Gradient Descent, it usually took a higher number of iterations to reach the minima, because of its randomness in its descent. Even though it requires a higher number of iterations to reach the minima than typical Gradient Descent, it is still computationally much less expensive than typical Gradient Descent. Hence, in most scenarios, SGD is preferred over Batch Gradient Descent for optimizing a learning algorithm.
S.NO.Batch Gradient DescentStochastic Gradient Descent
1.Computes gradient using the whole Training sampleComputes gradient using a single Training sample
2.Slow and computationally expensive algorithmFaster and less computationally expensive than Batch GD
3.Not suggested for huge training samples.Can be used for large training samples.
4.Deterministic in nature.Stochastic in nature.
5.Gives optimal solution given sufficient time to converge.Gives good solution but not optimal.
6.No random shuffling of points are required.The data sample should be in a random order, and this is why we want to shuffle the training set for every epoch.
7.Can’t escape shallow local minima easily.SGD can escape shallow local minima more easily.
8.Convergence is slow.Reaches the convergence much faster.    

Comments

Post a Comment

Popular posts from this blog

Mathematics for Machine Learning- CST 284 - KTU Minor Notes - Dr Binu V P

  Introduction About Me Syllabus Course Outcomes and Model Question Paper Question Paper July 2021 and evaluation scheme Question Paper June 2022 and evaluation scheme Overview of Machine Learning What is Machine Learning (video) Learn the Seven Steps in Machine Learning (video) Linear Algebra in Machine Learning Module I- Linear Algebra 1.Geometry of Linear Equations (video-Gilbert Strang) 2.Elimination with Matrices (video-Gilbert Strang) 3.Solving System of equations using Gauss Elimination Method 4.Row Echelon form and Reduced Row Echelon Form -Python Code 5.Solving system of equations Python code 6. Practice problems Gauss Elimination ( contact) 7.Finding Inverse using Gauss Jordan Elimination  (video) 8.Finding Inverse using Gauss Jordan Elimination-Python code Vectors in Machine Learning- Basics 9.Vector spaces and sub spaces 10.Linear Independence 11.Linear Independence, Basis and Dimension (video) 12.Generating set basis and span 13.Rank of a Matrix 14.Linear Mapping and Matri
Post a Comment
Read more

1.1 Solving system of equations using Gauss Elimination Method

Elementary Transformations Key to solving a system of linear equations are elementary transformations that keep the solution set the same, but that transform the equation system into a simpler form: Exchange of two equations (rows in the matrix representing the system of equations) Multiplication of an equation (row) with a constant  Addition of two equations (rows) Add a scalar multiple of one row to the other. Row Echelon Form A matrix is in row-echelon form if All rows that contain only zeros are at the bottom of the matrix; correspondingly,all rows that contain at least one nonzero element are on top of rows that contain only zeros. Looking at nonzero rows only, the first nonzero number from the left pivot (also called the pivot or the leading coefficient) is always strictly to the right of the  pivot of the row above it. The row-echelon form is where the leading (first non-zero) entry of each row has only zeroes below it. These leading entries are called pivots Example: $\begin
Post a Comment
Read more

4.3 Sum Rule, Product Rule, and Bayes’ Theorem

 We think of probability theory as an extension to logical reasoning Probabilistic modeling  provides a principled foundation for designing machine learning methods. Once we have defined probability distributions corresponding to the uncertainties of the data and our problem, it turns out that there are only two fundamental rules, the sum rule and the product rule. Let $p(x,y)$ is the joint distribution of the two random variables $x, y$. The distributions $p(x)$ and $p(y)$ are the corresponding marginal distributions, and $p(y |x)$ is the conditional distribution of $y$ given $x$. Sum Rule The addition rule states the probability of two events is the sum of the probability that either will happen minus the probability that both will happen. The addition rule is: $P(A∪B)=P(A)+P(B)−P(A∩B)$ Suppose $A$ and $B$ are disjoint, their intersection is empty. Then the probability of their intersection is zero. In symbols:  $P(A∩B)=0$  The addition law then simplifies to: $P(A∪B)=P(A)+P(B)$  wh
Post a Comment
Read more