Function sgd_entropic_regularization

ot/stochastic.py:463–534

r""" Compute the sgd algorithm to solve the regularized discrete measures optimal transport dual problem The function solves the following optimization problem: .. math:: \gamma = \mathop{\arg \min}_\gamma \quad \langle \gamma, \mathbf{M} \rangle_F + \mathrm{reg} \cdot\

(
    a, b, M, reg, batch_size, numItermax, lr, random_state=None
)

def sgd_entropic_regularization(
    a, b, M, reg, batch_size, numItermax, lr, random_state=None
):
    r"""
    Compute the sgd algorithm to solve the regularized discrete measures optimal transport dual problem

    The function solves the following optimization problem:

    .. math::
        \gamma = \mathop{\arg \min}_\gamma \quad \langle \gamma, \mathbf{M} \rangle_F +
        \mathrm{reg} \cdot\Omega(\gamma)

        s.t. \ \gamma \mathbf{1} = \mathbf{a}

             \gamma^T \mathbf{1} = \mathbf{b}

             \gamma \geq 0

    Where :

    - :math:`\mathbf{M}` is the (`ns`, `nt`) metric cost matrix
    - :math:`\Omega` is the entropic regularization term with :math:`\Omega(\gamma)=\sum_{i,j} \gamma_{i,j}\log(\gamma_{i,j})`
    - :math:`\mathbf{a}` and :math:`\mathbf{b}` are source and target weights (sum to 1)

    Parameters
    ----------
    a : ndarray, shape (ns,)
        source measure
    b : ndarray, shape (nt,)
        target measure
    M : ndarray, shape (ns, nt)
        cost matrix
    reg : float
        Regularization term > 0
    batch_size : int
        size of the batch
    numItermax : int
        number of iteration
    lr : float
        learning rate
    random_state : int, RandomState instance or None, default=None
        Determines random number generation. Pass an int for reproducible
        output across multiple function calls.

    Returns
    -------
    alpha : ndarray, shape (ns,)
        dual variable
    beta : ndarray, shape (nt,)
        dual variable

    References
    ----------
    .. [19] Seguy, V., Bhushan Damodaran, B., Flamary, R., Courty, N., Rolet, A.& Blondel, M. Large-scale Optimal Transport and Mapping Estimation. International Conference on Learning Representation (2018)
    """

    n_source = np.shape(M)[0]
    n_target = np.shape(M)[1]