def __init__(self, num_features, top_k_size):
self.D = num_features
self.learning_rate = 5e-1
self.cms = CustomCountMinSketch(2, (1 << 15) - 1)
# self.cms = CustomCountMinSketch(2, (1<<15) - 1)
self.top_k = TopK(top_k_size)
self.loss_val = 0
class LogisticRegression(object):
def __init__(self, count_sketch_size, top_k, feature_size):
self.learning_rate = 0.5
self.cms = CustomCountMinSketch(2, count_sketch_size)
self.top_k = TopK(top_k)
self.recovered_weight_vector = [0] * feature_size
def sigmoid(self, x):
if x >= 0:
return 1. / (1. + np.exp(-x))
else:
return np.exp(x) / (1. + np.exp(x))
def loss(self, y, p):
return -(y * math.log(p) + (1 - y) * math.log(1 - p))
def train_with_sketch(self, feature_pos, features, label):
logit = 0
min_logit = float("inf")
max_logit = float("-inf")
for i in range(len(feature_pos)):
# print("top k at pos {} value {}".format(feature_pos[i], self.top_k.get_item(feature_pos[i])))
val = self.top_k.get_value_for_key(feature_pos[i]) * features[i]
if val > max_logit:
max_logit = val
if val < min_logit:
min_logit = val
logit += val
if max_logit - min_logit == 0:
max_logit = 1
min_logit = 0
normalized_weights = (logit - min_logit) / (max_logit - min_logit)
print("normalized weights {}".format(normalized_weights))
sigm_val = self.sigmoid(normalized_weights)
print("label {} sigmoid {}".format(label, sigm_val))
loss = self.loss(y=label, p=sigm_val)
diff_label = (label - sigm_val) # difference in label
if diff_label != 0:
for i in range(len(feature_pos)):
# updating the change only on previous values
grad_update = self.learning_rate * diff_label * features[i]
value = self.cms.update(feature_pos[i], grad_update)
self.top_k.push(Node(feature_pos[i], value))
return loss
def predict(self, feature_pos, feature_val):
logit = 0
for i in range(len(feature_pos)):
logit += self.top_k.get_value_for_key(feature_pos[i]) * feature_val[i]
a = self.sigmoid(logit)
if a > 0.5:
return 1
else:
return 0
def sparse_recovery(self, feature_pos, feature_vals, label):
for i in range(len(feature_pos)):
cumulative_grad_val = self.cms.query(feature_pos[i])
self.recovered_weight_vector[feature_pos[i]-1] += cumulative_grad_val / feature_vals[i]
def __init__(self, num_features, top_k_size, learning_rate):
self.D = num_features
self.w = np.array([0] * self.D)
self.b = 0
self.learning_rate = learning_rate
self.cms = CustomCountMinSketch(2, (1 << 15) - 1)
self.top_k = TopK(top_k_size)
self.loss_val = 0
class LogisticRegression(object):
def __init__(self, num_features, top_k_size):
self.D = num_features
self.learning_rate = 5e-1
self.cms = CustomCountMinSketch(2, (1 << 15) - 1)
# self.cms = CustomCountMinSketch(2, (1<<15) - 1)
self.top_k = TopK(top_k_size)
self.loss_val = 0
def sigmoid(self, x):
if x >= 0:
return 1. / (1. + np.exp(-x))
else:
return np.exp(x) / (1. + np.exp(x))
def loss(self, y, p):
return -(y * math.log(p) + (1 - y) * math.log(1 - p))
def train_with_sketch(self, feature_pos, features, label):
logit = 0
min_logit = float("inf")
max_logit = float("-inf")
for i in range(len(feature_pos)):
# print("top k at pos {} value {}".format(feature_pos[i], self.top_k.get_item(feature_pos[i])))
# multiplying w[i] with x[i]
val = self.top_k.get_value_for_key(feature_pos[i]) * features[i]
if val > max_logit:
max_logit = val
if val < min_logit:
min_logit = val
# calculating wTx
logit += val
if max_logit - min_logit == 0:
max_logit = 1
min_logit = 0
normalized_weights = (logit - min_logit) / (max_logit - min_logit)
sigm_val = self.sigmoid(normalized_weights)
if sigm_val == 1.0:
sigm_val = sigm_val - (1e-5)
# print("label {} sigmoid {}".format(label, sigm_val))
gradient = (label - sigm_val)
loss = self.loss(y=label, p=sigm_val)
self.loss_val += loss
if gradient != 0:
for i in range(len(feature_pos)):
updated_val = self.learning_rate * gradient * features[i]
value = self.cms.update(feature_pos[i], updated_val)
self.top_k.push(Node(feature_pos[i], value))
return loss
def negative_log_likelihood(self, y, x):
return -y * x / (1 + math.exp(y))
def predict(self, feature_pos, feature_val):
logit = 0
for i in range(len(feature_pos)):
logit += self.top_k.get_value_for_key(
feature_pos[i]) * feature_val[i]
a = self.sigmoid(logit)
return a
class LogisticRegression(object):
def __init__(self, num_features):
self.D = num_features
self.learning_rate = 5e-1
# self.cms = CustomCountMinSketch(3, int(np.log(self.D) ** 2 / 3))
self.cms = CustomCountMinSketch(2, (1 << 18) - 1)
self.top_k = TopK(1 << 14 - 1)
def sigmoid(self, x):
if x >= 0:
return 1. / (1. + np.exp(-x))
else:
return np.exp(x) / (1. + np.exp(x))
def loss(self, y, p):
return -(y * math.log(p) + (1 - y) * math.log(1 - p))
def train_with_sketch(self, feature_pos, features, label):
logit = 0
min_logit = float("inf")
max_logit = float("-inf")
for i in range(len(feature_pos)):
# print("top k at pos {} value {}".format(feature_pos[i], self.top_k.get_item(feature_pos[i])))
val = self.top_k.get_value_for_key(feature_pos[i]) * features[i]
if val > max_logit:
max_logit = val
if val < min_logit:
min_logit = val
logit += val
if max_logit - min_logit == 0:
max_logit = 1
min_logit = 0
normalized_weights = (logit - min_logit) / (max_logit - min_logit)
print("normalized weights {}".format(normalized_weights))
sigm_val = self.sigmoid(normalized_weights)
print("label {} sigmoid {}".format(label, sigm_val))
loss = self.loss(y=label, p=sigm_val)
gradient = (label - sigm_val)
if gradient != 0:
for i in range(len(feature_pos)):
# updating the change only on previous values
updated_val = self.learning_rate * gradient * features[i]
value = self.cms.update(feature_pos[i], updated_val)
self.top_k.push(Node(feature_pos[i], value))
return loss
def predict(self, feature_pos, feature_val):
logit = 0
for i in range(len(feature_pos)):
logit += self.top_k.get_value_for_key(
feature_pos[i]) * feature_val[i]
a = self.sigmoid(logit)
if a > 0.5:
return 1
else:
return 0
def __init__(self, num_features):
self.D = num_features
self.learning_rate = 5e-1
# self.cms = CustomCountMinSketch(3, int(np.log(self.D) ** 2 / 3))
self.cms = CustomCountMinSketch(2, (1 << 18) - 1)
self.top_k = TopK(1 << 14 - 1)
def __init__(self, count_sketch_size, top_k, feature_size):
self.learning_rate = 0.5
self.cms = CustomCountMinSketch(2, count_sketch_size)
self.top_k = TopK(top_k)
self.recovered_weight_vector = [0] * feature_size