num_warmup, thin_step)
# marginal sampler
job.recompute_log_pdf = True
job.walltime = 60 * 60
# store results in home dir straight away
d = os.sep.join(os.path.abspath(__file__).split(os.sep)[:-1]) + os.sep
job.aggregator = MCMCJobResultAggregatorStoreHome(d)
return job
if __name__ == "__main__":
logger.setLevel(10)
num_repetitions = 10
# plain MCMC parameters, plan is to use every 200th sample
thin_step = 1
num_iterations = 5200
num_warmup = 200
compute_local = False
if not FileSystem.cmd_exists("sbatch") or compute_local:
engine = SerialComputationEngine()
else:
johns_slurm_hack = "#SBATCH --partition=intel-ivy,wrkstn,compute"
folder = os.sep + os.sep.join(["nfs", "data3", "ucabhst", modulename])
import os
from kmc.tools.Log import logger
import numpy as np
from scripts.experiments.trajectories.independent_jobs_classes.random_feats.StudentTrajectoryJob import StudentTrajectoryJob
from scripts.experiments.trajectories.tools import process
modulename = __file__.split(os.sep)[-1].split('.')[-2]
if __name__ == "__main__":
logger.setLevel(20)
nu_q = 1.
sigma_p = 1.
Ds = np.sort(2**np.arange(8))[::-1]
Ns = np.sort(
[50, 100, 200, 500, 1000, 2000, 3000, 4000, 5000, 10000, 20000])[::-1]
print(Ns)
print(Ds)
num_repetitions = 10
num_steps = 100
max_steps = 1000
step_size = .1
scale0 = 0.5
lmbda0 = 0.00008
job_generator = lambda D, N, m: StudentTrajectoryJob(N,
D,
m,
nu_q,
