lenskit.flexmf.FlexMFConfigBase
===============================

.. py:class:: lenskit.flexmf.FlexMFConfigBase
   :canonical: lenskit.flexmf._base.FlexMFConfigBase

   Bases: :py:obj:`lenskit.config.common.EmbeddingSizeMixin`, :py:obj:`pydantic.BaseModel`


   Common configuration for all FlexMF scoring components.

   :Stability: Experimental


   .. py:attribute:: embedding_size
      :type:  pydantic.PositiveInt
      :value: 64


      The dimension of user and item embeddings (number of latent features to
      learn).


   .. py:attribute:: batch_size
      :type:  int
      :value: 8192


      The training batch size.


   .. py:attribute:: learning_rate
      :type:  float
      :value: 0.01


      The learning rate for training.


   .. py:attribute:: epochs
      :type:  int
      :value: 10


      The number of training epochs.


   .. py:attribute:: regularization
      :type:  float
      :value: 0.01


      The regularization strength.

      .. note::
          The explicit-feedback model uses a different default strength.


   .. py:attribute:: reg_method
      :type:  Literal['AdamW', 'L2'] | None
      :value: 'AdamW'


      The regularization method to use.

      With the default AdamW regularization, training will use the
      :class:`~torch.optim.AdamW` optimizer with weight decay. With L2
      regularization, training will use sparse gradients and the
      :class:`torch.optim.SparseAdam` optimizer.

      .. note::
          The explicit-feedback model defaults this setting to ``"L2"``.

      ``None``
          Use no regularization.

      ``"L2"``
          Use L2 regularization on the parameters used in each training batch. The
          strength is applied to the _mean_ norms in a batch, so that the
          regularization term scale is not dependent on the batch size.

      ``"AdamW"``
          Use :class:`torch.optim.AdamW` with the specified regularization
          strength.  This configuration does *not* use sparse gradients, but
          training time is often comparable.

      .. note::
          Regularization values do not necessarily have the same range or meaning
          for the different regularization methods.