The .MLE
class evaluates the maximum likelihood estimate θ̂ of the model parameters, i.e.
θ̂ = argmaxΘ p(𝒟|θ)
Note: for a Gaussian-error model of the form 𝒟 = h(θ) + ϵ, ϵ ∼ N(0, σ) with fixed σ and independent measurements 𝒟i, maximizing the likelihood is mathematically equivalent to minimizing the sum of squared residuals ∑i(𝒟i−h(θ))2.
A numerical optimization procedure is performed to compute the MLE. By default, the :pyminimize
function of the :pyscipy.optimize
module is used, however other optimizers can be leveraged via the optimizer input of the .MLE
class.
The .MLE
class is imported using the following command:
>>> from UQpy.inference.MLE import MLE
UQpy.inference.MLE
UQpy.inference.MLE.mle
UQpy.inference.MLE.max_log_like
MLE Examples <../auto_examples/inference/mle/index>