def main(args):
fpath = "./dataset/{0}.dat".format(args.dname)
X, y = load_dat(fpath, minmax=(0, 1), normalize=False, bias_term=True)
N, dim = X.shape
nrep = args.rep
delta = args.delta
obj_clip = args.obj_clip
grad_clip = args.grad_clip
epsilon = [0.05, 0.1, 0.2, 0.4, 0.8, 1.6]
neps = len(epsilon)
K = 5 # 5-folds cross-validation
cv_rep = 2
k = 0
acc = np.zeros((neps, nrep, K * cv_rep))
obj = np.zeros((neps, nrep, K * cv_rep))
rkf = RepeatedKFold(n_splits=K, n_repeats=cv_rep)
for train, test in rkf.split(X):
train_X, train_y = X[train, :], y[train]
test_X, test_y = X[test, :], y[test]
n_train = train_X.shape[0]
for i, eps in enumerate(epsilon):
ipdb.set_trace()
rho = dp_to_zcdp(eps, delta)
for j in range(nrep):
sol = agd(train_X,
train_y,
rho,
eps,
delta,
logistic_grad,
logistic_loss,
logistic_test,
obj_clip,
grad_clip,
reg_coeff=args.reg_coeff,
batch_size=args.batch_size,
exp_dec=args.exp_dec,
gamma=args.gamma,
verbose=True)
obj[i, j, k] = logistic_loss(sol, train_X, train_y) / n_train
acc[i, j, k] = logistic_test(sol, test_X, test_y) * 100.0
# print "acc[{},{},{}]={}".format(i, j, k, acc[i, j, k])
k += 1
avg_acc = np.vstack([np.mean(acc, axis=(1, 2)), np.std(acc, axis=(1, 2))])
avg_obj = np.vstack([np.mean(obj, axis=(1, 2)), np.std(obj, axis=(1, 2))])
filename = "agd_logres_{0}".format(args.dname)
np.savetxt("{0}_acc.out".format(filename), avg_acc, fmt='%.5f')
np.savetxt("{0}_obj.out".format(filename), avg_obj, fmt='%.5f')
def main(args):
# load the dataset
fpath = "./dataset/{0}.dat".format(args.dname)
X, y = load_dat(fpath, minmax=(0, 1), normalize=False, bias_term=True)
N = X.shape[0]
delta = args.delta
obj_clip = args.obj_clip
grad_clip = args.grad_clip
# variables to change
epsilon = [0.1, 0.5, 1.0]
splits = [20, 40, 60, 80, 100, 120]
n_eps = len(epsilon)
n_rep = 10
n_splits = len(splits)
loss = np.zeros((n_eps, n_splits, n_rep))
acc = np.zeros((n_eps, n_splits, n_rep))
for k, eps in enumerate(epsilon):
rho = dp_to_zcdp(eps, delta)
print "rho = {:.5f}".format(rho)
for i, split in enumerate(splits):
for j in range(n_rep):
w = agd(X,
y,
rho,
eps,
delta,
logistic_grad,
logistic_loss,
logistic_test,
obj_clip,
grad_clip,
reg_coeff=0.0,
splits=split)
loss[k, i, j] = logistic_loss(w, X, y) / N
acc[k, i, j] = logistic_test(w, X, y)
avg_loss = np.mean(loss, axis=2)
avg_acc = np.mean(acc, axis=2)
np.savetxt('varying_splits_{0}_acc.out'.format(args.dname),
avg_acc,
fmt='%.5f')
np.savetxt('varying_splits_{0}_obj.out'.format(args.dname),
avg_loss,
fmt='%.5f')
def main(args):
# load the dataset
fpath = "./dataset/{0}.dat".format(args.dname)
X, y = load_dat(fpath, minmax=(0, 1), normalize=False, bias_term=True)
N = X.shape[0]
delta = args.delta
obj_clip = args.obj_clip
grad_clip = args.grad_clip
# variables to change
epsilon = [0.1, 0.2, 0.4, 0.8, 1.6]
gammas = [0.1, 0.2, 0.3, 0.4, 0.5]
n_eps = len(epsilon)
n_rep = 10
n_gammas = len(gammas)
loss = np.zeros((n_gammas, n_eps, n_rep))
acc = np.zeros_like(loss)
for i, gamma in enumerate(gammas):
for j, eps in enumerate(epsilon):
rho = dp_to_zcdp(eps, delta)
print "rho = {:.5f}".format(rho)
for k in range(n_rep):
w = agd(X,
y,
rho,
eps,
delta,
logistic_grad,
logistic_loss,
logistic_test,
obj_clip,
grad_clip,
reg_coeff=0.0,
gamma=gamma)
loss[i, j, k] = logistic_loss(w, X, y) / N
acc[i, j, k] = logistic_test(w, X, y)
avg_loss = np.mean(loss, axis=2)
avg_acc = np.mean(acc, axis=2)
np.savetxt('varying_gamma_{0}_acc.out'.format(args.dname),
avg_acc,
fmt='%.5f')
np.savetxt('varying_gamma_{0}_obj.out'.format(args.dname),
avg_loss,
fmt='%.5f')