neural_network.optimizers.adagrad
=================================

.. py:module:: neural_network.optimizers.adagrad

.. autoapi-nested-parse::

   Adagrad Optimizer

   Implements Adagrad (Adaptive Gradient) for neural network training using NumPy.
   Adagrad adapts the learning rate for each parameter based on historical gradients.

   Reference: https://en.wikipedia.org/wiki/Stochastic_gradient_descent#AdaGrad
   Author: Adhithya Laxman Ravi Shankar Geetha
   Date: 2025.10.22



Attributes
----------

.. autoapisummary::

   neural_network.optimizers.adagrad.optimizer


Classes
-------

.. autoapisummary::

   neural_network.optimizers.adagrad.Adagrad


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

.. py:class:: Adagrad(learning_rate: float = 0.01, epsilon: float = 1e-08)

   Adagrad optimizer.

   Adapts learning rate individually for each parameter:
       accumulated_grad += gradient^2
       param = param - (learning_rate / sqrt(accumulated_grad + epsilon)) * gradient


   .. py:method:: update(param_id: int, params: numpy.ndarray, gradients: numpy.ndarray) -> numpy.ndarray

      Update parameters using Adagrad.

      Args:
          param_id (int): Unique identifier for parameter group.
          params (np.ndarray): Current parameters.
          gradients (np.ndarray): Gradients of parameters.

      Returns:
          np.ndarray: Updated parameters.

      >>> optimizer = Adagrad(learning_rate=0.1)
      >>> params = np.array([1.0, 2.0])
      >>> grads = np.array([0.1, 0.2])
      >>> updated = optimizer.update(0, params, grads)
      >>> updated.shape
      (2,)



   .. py:attribute:: accumulated_grad
      :type:  dict[int, numpy.ndarray]


   .. py:attribute:: epsilon
      :value: 1e-08



   .. py:attribute:: learning_rate
      :value: 0.01



.. py:data:: optimizer