# possible to change
D = 2
N = 1000
# target is banana density, fallback to Gaussian if theano is not present
if banana_available:
target = Banana(D=D)
else:
target = IsotropicZeroMeanGaussian(D=D)
samplers = [
StandardMetropolis(target, D),
AdaptiveMetropolis(target, D),
KernelAdaptiveMetropolis(target, D, N=200)
]
for sampler in samplers:
# MCMC parameters, feel free to increase number of iterations
start = np.zeros(D)
num_iter = 1000
# run MCMC
samples, proposals, accepted, acc_prob, log_pdf, times, step_sizes = mini_mcmc(sampler, start, num_iter, D)
visualise_trace(samples, log_pdf, accepted, step_sizes)
plt.suptitle("%s, acceptance rate: %.2f" % \
(sampler.__class__.__name__, np.mean(accepted)))
plt.show()
# kmc sampler instance, schedule here also controls updating the surrogate
# this is a very liberate schedule, i.e. constant adaptation
# necessary if KMC is not initialised with oracle samples
schedule = lambda t: 0.001
acc_star = 0.7
kmc = KMC(surrogate, target, momentum, num_steps_min, num_steps_max,
step_size_min, step_size_max, schedule, acc_star)
# MCMC parameters
# set to around 5000-10000 iterations to have KMC lite explored all of the support
start = np.zeros(D)
start[1] = -3
num_iter = 500
# run MCMC
samples, proposals, accepted, acc_prob, log_pdf, times, step_sizes = mini_mcmc(
kmc, start, num_iter, D)
visualise_trace(samples,
log_pdf,
accepted,
log_pdf_density=surrogate,
step_sizes=step_sizes)
plt.suptitle("KMC lite %s, acceptance rate: %.2f" % \
(surrogate.__class__.__name__, np.mean(accepted)))
# now initialise KMC finite with the samples from the surrogate, and run for more
# learn parameters before starting
thinned = samples[np.random.permutation(len(samples))[:N]]
surrogate2 = KernelExpFiniteGaussian(sigma=2, lmbda=0.001, D=D, m=N)
surrogate2.set_parameters_from_dict(
BayesOptSearch(surrogate2, thinned, {
if glass_available:
target = GlassPosterior()
target.set_up()
else:
target = IsotropicZeroMeanGaussian(D=D)
# transition kernel, pick any
samplers = [
get_am_instance(target),
get_mh_instance(target),
get_kam_instance(target),
get_kmc_instance(target)
]
for sampler in samplers:
# MCMC parameters
# small number of iterations here to keep runtime short, feel free to increase
start = np.zeros(D)
num_iter = 50
# run MCMC
samples, proposals, accepted, acc_prob, log_pdf, times, step_sizes = mini_mcmc(sampler, start, num_iter, D)
visualise_trace(samples, log_pdf, accepted, step_sizes, idx0=1, idx1=6)
plt.suptitle("%s on %s, acceptance rate: %.2f" % \
(sampler.__class__.__name__, target.__class__.__name__, np.mean(accepted)))
plt.show()
# this is a very liberate schedule, i.e. constant adaptation
# necessary if KMC is not initialised with oracle samples
schedule = lambda t: 0.001
acc_star = 0.7
kmc = KMC(surrogate, target,
momentum, num_steps_min, num_steps_max, step_size_min, step_size_max,
schedule, acc_star)
# MCMC parameters
# set to around 5000-10000 iterations to have KMC lite explored all of the support
start = np.zeros(D)
start[1] = -3
num_iter = 500
# run MCMC
samples, proposals, accepted, acc_prob, log_pdf, times, step_sizes = mini_mcmc(kmc, start, num_iter, D)
visualise_trace(samples, log_pdf, accepted, log_pdf_density=surrogate, step_sizes=step_sizes)
plt.suptitle("KMC lite %s, acceptance rate: %.2f" % \
(surrogate.__class__.__name__, np.mean(accepted)))
# now initialise KMC finite with the samples from the surrogate, and run for more
# learn parameters before starting
thinned = samples[np.random.permutation(len(samples))[:N]]
surrogate2 = KernelExpFiniteGaussian(sigma=2, lmbda=0.001, D=D, m=N)
surrogate2.set_parameters_from_dict(BayesOptSearch(surrogate2, thinned, {'sigma': [-3,3]}).optimize(3))
surrogate2.fit(thinned)
# now use conservative schedule, or None at all if confident in oracle samples
schedule2 = lambda t: 0.01 if t < 3000 else 0.
kmc2 = KMC(surrogate2, target,
