machine_learning.mini_batch_gradient_descent
============================================

.. py:module:: machine_learning.mini_batch_gradient_descent

.. autoapi-nested-parse::

   Mini-Batch Gradient Descent : https://en.wikipedia.org/wiki/Stochastic_gradient_descent
   Mini-batch gradient descent is an optimization method for training models
   by splitting the data into small batches.



Functions
---------

.. autoapisummary::

   machine_learning.mini_batch_gradient_descent.mini_batch_gradient_descent


Module Contents
---------------

.. py:function:: mini_batch_gradient_descent(feature_matrix: numpy.ndarray, target_values: numpy.ndarray, learning_rate: float = 0.01, batch_size: int = 16, n_epochs: int = 50, random_seed: int | None = None) -> tuple[numpy.ndarray, float]

   Mini-Batch Gradient Descent for linear regression.

   Parameters
   ----------
   feature_matrix: Feature matrix.
   target_values: Target values.
   learning_rate: Learning rate.
   batch_size: Size of mini-batches.
   n_epochs: Number of training epochs.
   random_seed: Random seed for reproducibility.

   Returns
   -------
   weights: Learned weights.
   bias: Learned bias.

   Example
   -------
   >>> import numpy as np
   >>> X = np.array([[1], [2], [3], [4]])
   >>> y = np.array([2, 4, 6, 8])
   >>> w, b = mini_batch_gradient_descent(
   ...     X, y, learning_rate=0.1, batch_size=2, n_epochs=100, random_seed=42
   ... )
   >>> round(float(w[0]), 1)  # slope close to 2
   2.0