zhusuan.mcmc.SGMCMC

class SGMCMC[source]

Bases: jittor.Module

Base class for stochastic gradient MCMC (SGMCMC) algorithms.

SGMCMC is a class of MCMC algorithms which utilize stochastic gradients instead of the true gradients.

The typical code for SGMCMC inference is like:

sgmcmc = zs.mcmc.SGLD(learning_rate=lr)
net = BayesianNet()
for epoch in range(epoch_size):
    for step in range(num_batches):
        w_samples = model.sample(net, {'x': x, 'y': y})

        for i, (k, w) in enumerate(w_samples.items()):
            # Utilize stochastic gradients by samples and update parameters.
            ...
execute(bn, observed, resample=False, step=1)[source]
initialize()[source]
sample(bn, observed, resample=False, step=1)[source]

Running one sgmcmc iteration.

Parameters

  • bn – A instance of BayesianNet.

  • observed – A dictionary of (string, Tensor) pairs. Mapping from names of observed StochasticTensor s to their values.

  • resample – Flag indicates if the sampler need get the var list of the BayesianNet instance, usually set to True on first sgmcmc iteration.

Returns

A list of Var, samples generated by sgmcmc iteration.