Out of Core Learning

Sometimes datasets which we’d like to train on can’t fit in memory but we’d still like to get an exact update. pomegranate supports out of core training to allow this, by allowing models to summarize batches of data into sufficient statistics and then later on using these sufficient statistics to get an exact update for model parameters. These are done through the methods `model.summarize` and `model.from_summaries`. Let’s see an example of using it to update a normal distribution.

>>> from pomegranate import *
>>> import numpy
>>>
>>> a = NormalDistribution(1, 1)
>>> b = NormalDistribution(1, 1)
>>> X = numpy.random.normal(3, 5, size=(5000,))
>>>
>>> a.fit(X)
>>> a
{
    "frozen" :false,
    "class" :"Distribution",
    "parameters" :[
        3.012692830297519,
        4.972082359070984
    ],
    "name" :"NormalDistribution"
}
>>> for i in range(5):
>>>     b.summarize(X[i*1000:(i+1)*1000])
>>> b.from_summaries()
>>> b
{
    "frozen" :false,
    "class" :"Distribution",
    "parameters" :[
        3.01269283029752,
        4.972082359070983
    ],
    "name" :"NormalDistribution"
}

This is a simple example with a simple distribution, but all models and model stacks support this type of learning. Lets next look at a simple Bayesian network.

We can see that before fitting to any data, the distribution in one of the states is equal for both. After fitting the first distribution they become different as would be expected. After fitting the second one through summarize the distributions become equal again, showing that it is recovering an exact update.

FAQ

  1. How many examples should I summarize at a time?

  1. You should summarize the largest amount of data that fits in memory. The larger the block of data, the more efficient the calculations can be, particularly if GPU computing is being used.

  1. Can I still do multi-threading / use a GPU with out-of-core learning?

  1. Absolutely. You will have to call joblib yourself if you use the formulation above but the computational aspects of the call to summarize have the GIL released and so multi-threading can be used.

  1. Does out of core learning give exact or approximate updates?

  1. It gives exact updates as long as the total set of examples that are summarized is the same. Sufficient statistics are collected for each of the batches and are equal to the sufficient statistics that one would get from the full dataset. However, the initialization step is done on only a single batch. This may cause the final models to differ due simply to the different initializations. If one has pre-defined initializations and simply calls fit, then the exact same model will be yielded.