Quadratic Deep¶
-
class
deepobs.tensorflow.testproblems.quadratic_deep.
quadratic_deep
(batch_size, l2_reg=None)[source]¶ DeepOBS test problem class for a stochastic quadratic test problem
100
dimensions. The 90 % of the eigenvalues of the Hessian are drawn from theinterval \((0.0, 1.0)\) and the other 10 % are from \((30.0, 60.0)\) simulating an eigenspectrum which has been reported for Deep Learning https://arxiv.org/abs/1611.01838.This creatis a loss functions of the form
\(0.5* (\theta - x)^T * Q * (\theta - x)\)
with Hessian
Q
and "data"x
coming from the quadratic data set, i.e., zero-mean normal.Parameters: - batch_size (int) -- Batch size to use.
- l2_reg (float) -- No L2-Regularization (weight decay) is used in this
test problem. Defaults to
None
and any input here is ignored.
-
dataset
¶ The DeepOBS data set class for the quadratic test problem.
-
train_init_op
¶ A tensorflow operation initializing the test problem for the training phase.
-
train_eval_init_op
¶ A tensorflow operation initializing the test problem for evaluating on training data.
-
test_init_op
¶ A tensorflow operation initializing the test problem for evaluating on test data.
-
losses
¶ A tf.Tensor of shape (batch_size, ) containing the per-example loss values.
-
regularizer
¶ A scalar tf.Tensor containing a regularization term. Will always be
0.0
since no regularizer is used.