Skip to main content

5.3 Stochastic Gradient Descent



Computing the gradient can be very time consuming. However, often it is possible to find a “cheap” approximation of the gradient. Approximating the gradient is still useful as long as it points in roughly the same direction as the true gradient. 

Stochastic gradient descent (often shortened as SGD) is a stochastic approximation of the gradient descent method for minimizing an objective function that is written as a sum of differentiable functions. The word
stochastic here refers to the fact that we acknowledge that we do not know the gradient precisely, but  instead only know a noisy approximation to it. By constraining the probability distribution of the approximate gradients, we can still theoretically guarantee that SGD will converge.

In machine learning, given $n = 1,\ldots,N$ data points, we often consider objective functions that are the sum of the losses $L(\theta)$ incurred by each example $n$. In mathematical notation, we have the form

$L(\theta)=\sum_{n=1}^N L_n(\theta)$ 

where $\theta$ is the vector of parameters of interest.i.e., we want to find $\theta$ that minimizes $L$.An example is the negative log likelihood  function, which is expressed as a sum over log-likelihoods of individual examples so that

$L(\theta)=-\sum_{n=1}^N log(p(y_n|x_n,\theta)$ 

where $x_n \in \mathbb{R}^D$ are the training inputs, $y_n$ are the training targets, and $\theta$ are the parameters of the regression model.

Standard gradient descent, as introduced previously, is a “batch” optimization method, i.e., optimization is performed using the full training set by updating the vector of parameters according to

$\theta_{i+1}=\theta_i-\gamma_i(\bigtriangledown L(\theta_i))^T=\theta_i-\gamma_i\sum_{n=1}^N( \bigtriangledown L_n(\theta_i))^T$

for a suitable step-size parameter $\gamma_i$. Evaluating the sum gradient may require expensive evaluations of the gradients from all individual functions $L_n$. When the training set is enormous and/or no simple formulas exist,evaluating the sums of gradients becomes very expensive.

Consider the term $\sum_{n=1}^{N}\bigtriangledown L_n(\theta_i)$,  we can reduce the amount of computation by taking a sum over a smaller set of  $L_n$. In contrast to batch gradient descent, which uses all $L_n$ for $n = 1,\ldots,N$, we randomly choose a subset of $L_n$ for mini-batch gradient descent. In the extreme case, we randomly select only a single $L_n$  to estimate the gradient. The key insight about why taking a subset of data is sensible is to realize that for gradient descent to converge, we only require that the gradient is an unbiased estimate of the true gradient. In fact the term $\sum_{n=1}^{N} \bigtriangledown L_n(\theta_i)$ is an empirical estimate of the expected value  of the gradient. Therefore, any other unbiased empirical estimate of the expected value, for example using any subsample of the data, would suffice for convergence of gradient descent.

Why should one consider using an approximate gradient? A major reason is practical implementation constraints, such as the size of central processing unit (CPU)/graphics processing unit (GPU) memory or limits on computational time. We can think of the size of the subset used to estimate the gradient in the same way that we thought of the size of a sample when estimating empirical means . Large mini-batch sizes will provide accurate estimates of the gradient, reducing the variance in the parameter update. Furthermore, large mini-batches take advantage of highly optimized matrix operations in vectorized implementations of the cost and gradient. The reduction in variance leads to more stable convergence, but each gradient calculation will be more expensive.

In contrast, small mini-batches are quick to estimate. If we keep the mini-batch size small, the noise in our gradient estimate will allow us to get out of some bad local optima, which we may otherwise get stuck in.In machine learning, optimization methods are used for training by minimizing an objective function on the training data, but the overall goal is to improve generalization performance . Since the goal in machine learning does not necessarily need a precise estimate of the minimum of the objective function, approximate gradients using mini-batch approaches have been widely used. Stochastic gradient descent is very effective in large-scale machine learning problems ,such as training deep neural networks on millions of images,reinforcement learning,or training of large-scale Gaussian process models

Example:
Consider the update equation for stochastic gradient descent. Write down the update when we use a mini-batch size of one.
$\theta_{i+1}=\theta_i-\gamma_i(\bigtriangledown L(\theta_i))^T=\theta_i-\gamma_i\sum_{n=1}^N( \bigtriangledown L_n(\theta_i))^T$

$\theta_{i+1}=\theta_i-\gamma_i(\bigtriangledown L_k(\theta_i))^T$
where $k$ is the index of the example that is randomly chosen.

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 University Question Papers and Evaluation Scheme -Mathematics for Machine learning CST 284 KTU 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...
Post a Comment
Read more

Vectors in Machine Learning

As data scientists we work with data in various formats such as text images and numerical values We often use vectors to represent data in a structured and efficient manner especially in machine learning applications In this blog post we will explore what vectors are in terms of machine learning their significance and how they are used What is a Vector? In mathematics, a vector is a mathematical object that has both magnitude and direction. In machine learning, a vector is a mathematical representation of a set of numerical values. Vectors are usually represented as arrays or lists of numbers, and each number in the list represents a specific feature or attribute of the data. For example, suppose we have a dataset of houses, and we want to predict their prices based on their features such as the number of bedrooms, the size of the house, and the location. We can represent each house as a vector, where each element of the vector represents a specific feature of the house, such as the nu...
Post a Comment
Read more

2.14 Singular Value Decomposition

The Singular Value Decomposition ( SVD) of a matrix is a central matrix decomposition method in linear algebra.It can be applied to all matrices,not only to square matrices and it always exists.It has been referred to as the 'fundamental theorem of linear algebra'( strang 1993). SVD Theorem: Let $A^{m \times n}$ be a rectangular matrix of rank $r \in [0,min(m,n)]$. The SVD of A is a decomposition of the form. $A= U \Sigma V^T $ with an orthogonal matrix $U \in \mathbb{R}^{m \times m}$ with column vectors $u_i, i=1,\ldots,m$ and an orthogonal matrix $V \in \mathbb{R}^{n \times n}$ with column vectors $v_j, j=1,\ldots,n$.Moreover, $\Sigma$ is an $m \times n$ matrix with $\sum_{ii} = \sigma \ge 0$ and $\sigma_{ij}=0, i \ne j$. The diagonal entries $\Sigma_i=1,\ldots,r$ of $\sigma$ are called singular values . $u_i$ are called left singular vectors , and $v_j$ are called right singular vectors .By convention singular values are ordered ie; $\sigma_1 \ge \sigma_2 \ldots \sigma_r \...
Post a Comment
Read more