Pinned Loading

1. python method chaining without monads python method chaining without monads

   1

   import functools

   2

   from joblib import Parallel, delayed

   3

   4

   def compose2(f, g):

   5

       return lambda x: g(f(x))

2. mine.py mine.py

   1

   2

   class MINE(nn.Module):

   3

       """

   4

       Stub to implement Mutual Information Neural Estimation.

   5

       See https://arxiv.org/pdf/1801.04062

3. Solving mnist, fast and short Solving mnist, fast and short

   1

   from torchvision.datasets import MNIST

   2

   import numpy as np

   3

   4

   def data(train):

   5

       mnist = MNIST(root='.', download=True, train=train)

4. leverage_scores.py leverage_scores.py

   1

   # leverage scores l_[i] = tr(X @ (X^T X)^-1 @ X)

   2

   # indication of self-sensitivity or self-influence of i-th sample.

   3

   import numpy as np

   4

   5

   n = 2048 # samples

5. approximate_joint_diagonalization approximate_joint_diagonalization Public

   parallel joint diagonlization

   Python 7 3