What happens when you increase the regularization hyperparameter lambda?

The regularization constant, $$\lambda$$, is a nonnegative hyperparameter that characterizes the trade-off between standard prediction loss and a regularization penalty. It is typically fit using validation data. When $$\lambda = 0$$, the original loss function is recovered, while larger values of $$\lambda$$ constrain the model's weights more considerably. For example, in weight decay ($$\ell_2$$ regularization), it modifies the objective to $$L(\mathbf{w}, b) + \frac{\lambda}{2} \|\mathbf{w}\|^2$$, where the penalty term is conventionally divided by 2 so that the constant cancels out gracefully when taking the derivative.

University of Michigan - Ann Arbor

Claude

Google

Weight decay, commonly known as $$\ell_2$$ regularization, is a widely used technique for regularizing parametric machine learning models. Instead of directly manipulating the number of parameters, weight decay operates by restricting the values that the parameters can take. The technique is motivated by the intuition that the simplest function is $$f = 0$$, and the complexity of a linear function, such as $$f(\mathbf{x}) = \mathbf{w}^	op \mathbf{x}$$, can be measured by the distance of its parameters from zero.

Weight Decay

Unlike $$\ell_2$$ regularization which distributes weights evenly, $$\ell_1$$ regularization penalizes the absolute values of the weights. This leads to models that concentrate weights on a small set of features by clearing the other weights to zero, making it an effective method for feature selection. If a model only relies on a few features, it may eliminate the need to collect, store, or transmit data for the dropped features. Linear models that are $$\ell_1$$-regularized are popularly known as lasso regression.

L1 Regularization

Hyperparameters related to neural network structure:
- Number of hidden layers (Depth)
- Number of hidden units (Width)
- Dropout method
- Activation function for each layer
- Weights Initialization

Hyperparameters related to training algorithm:
- Learning rate $$\alpha$$
- Momentum parameter $$\beta \sim 0.9$$
- $$\beta_1 \sim 0.9, \beta_2 \sim 0.999, \epsilon \sim 10^{-8}$$
- Number of Gradient descent iterations
- Mini-batch size
- Optimizer algorithm
- Learning rate decay
- Regularization rate $$\lambda$$

List of Common Hyperparameters in Deep Learning

Dive into Deep Learning

In machine learning _Frobenius_ and _L2_ norms can be used interchangeably. Nevertheless there is slight difference between these two. _L2_ norm in essence is an Euclidean norm with special case, when p=2. More specifically for n-dimensional vector we will have:
   $$L_2 = \sqrt {\textstyle\sum_{i=1}^n x_{i}^{2}}$$.
The _Frobenius_ measures the same thing but in this case we have matrices. That's why in neural networks _L2_ norm is frequently referred as _Forbenius_ norm.

_Frobenius_ and _L2_

In ridge regression, the model coefficients and bias are learned using the least-squares criterion with an added penalty for large coefficients. The parameters are found by minimizing an objective function that includes a tuning parameter (often denoted as $$\lambda$$ or $$\alpha$$) to control the strength of this penalty term. Once the parameters are learned, the prediction formula is the same as in ordinary least squares (OLS).

Ridge regression uses $$L_2$$ regularization (weight decay), which adds the sum of the squared coefficients to the residual sum of squares (RSS):

$$RSS_{RIDGE}(\beta_{j}, \beta_{0}) = \sum_{i=1}^{n} ({y}_{i}-{\beta}_{0}-\sum_{j=1}^{p}{\beta}_{j}{x}_{ij})^2 +\lambda\sum_{j=1}^{p}{\beta}_{j}^2=RSS+\lambda\sum_{j=1}^{p}{\beta}_{j}^2$$

A higher tuning parameter ($$\lambda$$ or $$\alpha$$) results in more regularization and a simpler model. Ridge regression is especially useful when the number of predictor variables is greater than the number of observations. Because the penalty term is sensitive to the scale of the variables, predictors should usually be standardized before applying ridge regression.

Ridge Regression

What is weight decay?

A normal distribution, also known as a Gaussian distribution, is a continuous probability distribution defined by its mean $$\mu$$ and variance $$\sigma^2$$ (where $$\sigma$$ is the standard deviation). The probability density function is given by the formula: $$p(x) = \frac{1}{\sqrt{2 \pi \sigma^2}} \exp\left(-\frac{1}{2 \sigma^2} (x - \mu)^2ight)$$. Changing the mean $$\mu$$ corresponds to a shift of the distribution along the $$x$$-axis, while increasing the variance $$\sigma^2$$ spreads the distribution out and lowers its peak.

Gaussian (Normal) Distribution

Regularization Constant

In deep learning, typical strengths of weight decay (such as $$\ell_2$$ regularization) are usually insufficient to prevent highly parameterized networks from fully interpolating the training data. While these regularizers were classically thought to restrict models from fitting arbitrary labels, their effectiveness in deep architectures is often contingent on being paired with an early stopping criterion.

Insufficiency of Weight Decay for Preventing Interpolation

Lasso regression is similar to ridge regression, but instead uses the $$\ell_1$$ regularization penalty. This has the effect of setting some coefficient estimates to exactly zero for the least influential variables, which leads to models only including a subset of variables. This results in a sparse solution, which is a kind of feature selection. The parameter $$\lambda$$ controls the amount of $$\ell_1$$ regularization. The prediction formula is the same as ordinary least squares (OLS), but it minimizes the following objective function: $$RSS_{LASSO}(\beta_{j}, \beta_{0}) = \sum_{i=1}^{n} ({y}_{i}-{\beta}_{0}-\sum_{j=1}^{p}{\beta}_{j}{x}_{ij})^2 +\lambda\sum_{j=1}^{p}\vert{\beta}_{j}\vert=RSS+\lambda\sum_{j=1}^{p}\vert{\beta}_{j}\vert$$

Lasso Regression

For a feedforward neural network, the depth of the network is the number of hidden layers plus one (as the output layer is also parameterized). The width of the network is the dimensionality of its hidden layers.

The main architectural considerations for designing a neural network are choosing the depth of the network and the width of each layer.


Depth and Width for Neural Networks

Dropout means what percentage of neurons should be randomly “killed” during each epoch to prevent overfitting.

Dropout

Neural network learning rate means how fast the backpropagation algorithm performs gradient descent. A larger learning rate makes the network train faster but might result in missing the minimum of the loss function.

Neural Network Learning Rate

When you try to train a huge amount of data with limited computer memory, you can separate the whole training set to several batches that can fit into your computer memory. Then you feed these batches to your model one by one. After feeding all batches once, you complete one epoch. To successfully train your model, you need multiple epochs.

Epochs in Machine Learning

In a neural network, numeric data points, called inputs, are fed into the neurons in the input layer. Each neuron has a weight, and multiplying the input number with the weight gives the output of the neuron, which is transferred to the next layer.
The activation function is a mathematical “gate” in between the input feeding the current neuron and its output going to the next layer. It can be as simple as a step function that turns the neuron output on and off, depending on a rule or threshold. Or it can be a transformation that maps the input signals into output signals that are needed for the neural network to function.
Activation functions are mathematical equations that determine the output of a neural network. The function is attached to each neuron in the network, and determines whether it should be activated (“fired”) or not, based on whether each neuron’s input is relevant for the model’s prediction. Activation functions also help normalize the output of each neuron to a range between 1 and 0 or between -1 and 1. When used in a multilayer neural network, activation functions can be different for different layers. 

Activation Functions in Neural Networks

When a neural network trains, it uses an algorithm to determine the optimal weights for the model, called an optimizer. 
There are several optimizer algorithms, such as:
- Gradient descent
- Mini-batch gradient descent
- Gradient descent with momentum
- RMSprop
- Adam optimization algorithm
- Nesterov momentum
- AdaGrad

Deep Learning Optimizer Algorithms

Initial weights are applied to all the neurons.
It is necessary to set initial weights for the first forward pass. Two basic options are to set weights to zero or to randomize them. However, this can result in a vanishing or exploding gradient, which will make it difficult to train the model. To mitigate this problem, you can use a heuristic (a formula tied to the number of neuron layers) to determine the weights. A common heuristic used for the Tanh activation is called Xavier initialization.

On top of that if the architecture being used has already been trained by someone else (such as ImageNet) the node values can be initialized to those values. This is known as transfer learning and it can be very useful to substantially increase training speed and model accuracy.

Deep Learning Weight Initialization

- Grid search
- Randomly choosing
- Coarse to fine

Hyperparameters Tuning Methods in Deep Learning

Batch normalization is a technique designed to accelerate and stabilize the training of deep neural networks. Mechanistically, it centers and rescales the intermediate layer activations back to a controlled mean and variance, preventing their distributions from diverging across layers and over time. By keeping these intermediate values on a comparable scale, batch normalization enables the use of more aggressive learning rates. The technique was originally motivated by the concept of covariate shift applied to internal layers, but the hypothesis that it works by reducing this so-called internal covariate shift has since been challenged and does not appear to be a valid explanation for its effectiveness. Although intuitively thought to make the optimization landscape smoother, the precise mechanism by which batch normalization aids training remains an open research question. Despite this theoretical uncertainty, batch normalization has proven indispensable in practice, being applied in nearly all deployed image classifiers and earning the original paper tens of thousands of citations.

Learn Before

Related

Learn After