A square matrix where and and are two variables.
There are three types of covariance matrix:
- Full - All entries are specified. Has parameters for variables.
- Diagonal - The matrix is diagonal, meaning all off-diagonal entries are zero. Variances can differ across dimensions but there is no interplay between the dimensions. Has parameters.
- Spherical - The matrix is equal to the identity matrix multiplied by a constant. This means the variance is the same in all dimensions. Has parameters.
A valid covariance matrix is always symmetric and positive semi-definite.
Only applicable to positive numbers.
When the error of a model is correlated with one or more of the features.
A moving average smooths a sequence of observations.
Exponential moving average (EMA)¶
A type of moving average in which the influence of past observations on the current average diminishes exponentially with time.
is the moving average at time , is the input at time and is a hyperparameter. As decreases, the moving average weights recent observations more strongly.
If we initialise the EMA to equal zero () it will be very biased towards zero around the start. To correct this we can start with being close to 0 and gradually increase it. This effect can be achieved by rewriting the formula as:
See Adam: A Method for Stochastic Optimization, Kingma et al. (2015) for an example of this bias correction being used in practice.
An estimate for a parameter.
Measures the asymmetry of a probability distribution.
The square root of the variance. The formula is:
where is the mean of X.
Sample standard deviation¶
Note that the above is the biased estimator for the sample standard deviation. Estimators which are unbiased exist but they each only apply to some population distributions.