Packages

final class EMLDAOptimizer extends LDAOptimizer

Optimizer for EM algorithm which stores data + parameter graph, plus algorithm parameters.

Currently, the underlying implementation uses Expectation-Maximization (EM), implemented according to the Asuncion et al. (2009) paper referenced below.

References:

  • Original LDA paper (journal version): Blei, Ng, and Jordan. "Latent Dirichlet Allocation." JMLR, 2003.
    • This class implements their "smoothed" LDA model.
  • Paper which clearly explains several algorithms, including EM: Asuncion, Welling, Smyth, and Teh. "On Smoothing and Inference for Topic Models." UAI, 2009.
Annotations
@Since( "1.4.0" )
Source
LDAOptimizer.scala
Linear Supertypes
LDAOptimizer, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. EMLDAOptimizer
  2. LDAOptimizer
  3. AnyRef
  4. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new EMLDAOptimizer()

Value Members

  1. def getKeepLastCheckpoint: Boolean

    If using checkpointing, this indicates whether to keep the last checkpoint (vs clean up).

    If using checkpointing, this indicates whether to keep the last checkpoint (vs clean up).

    Annotations
    @Since( "2.0.0" )
  2. def setKeepLastCheckpoint(keepLastCheckpoint: Boolean): EMLDAOptimizer.this.type

    If using checkpointing, this indicates whether to keep the last checkpoint (vs clean up).

    If using checkpointing, this indicates whether to keep the last checkpoint (vs clean up). Deleting the checkpoint can cause failures if a data partition is lost, so set this bit with care.

    Default: true

    Annotations
    @Since( "2.0.0" )
    Note

    Checkpoints will be cleaned up via reference counting, regardless.