4
3

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 3 years have passed since last update.

Linear層から出した分散共分散行列をMultivariateNormalに渡すときに ~ is zero, singular U のエラーが出る

Last updated at Posted at 2020-10-08

やったこと

pytorchはv1.5.1を使用.
Linearの出力を(x, y, vxx, vyy, vxy)として,分散共分散行列を作りMultivariateNormalに渡す.

fc = nn.Linear(n, 5)
output = fc(x)
mean = output[:2]
vxx, vyy = nn.Softplus()(output[2:4])
vxy = output[-1]

covariance_matrix = torch.zeros(2, 2)
covariance_matrix[0, 0] += vxx
covariance_matrix[0, 1] += vxy
covariance_matrix[1, 0] += vxy
covariance_matrix[1, 1] += vyy

dist = MultivariateNormal(mean, covariance_matrix)

RuntimeError: cholesky_cuda: For batch 0: U(6,6) is zero, singular U.

MultivariateNormalでは分散共分散行列をコレスキー分解しているため,正定値行列を与える必要がある.このままではcovariance_matrixが正定値行列であることを保証していないので上記エラーが起こる.

解決法: コレスキー分解後の下三角行列を渡す.

fc = nn.Linear(n, 5)
output = fc(x)
mean = output[:2]
a, c = nn.Softplus()(output[2:4])
b = output[-1]

L = torch.zeros(2, 2)
L[0, 0] += a
L[1, 0] += b
L[1, 1] += c

dist = MultivariateNormal(mean,  scale_tril=L)

scale_tril (Tensor) – lower-triangular factor of covariance, with positive-valued diagonal

とあるので対角成分の$a, c$はsoftplusで正の値にしている.

分散共分散行列にするときにはコレスキー分解

\Sigma = LL^{T}

に従い,

covariance_matrix = np.dot(L, L.T)

とすればよい.

4
3
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
4
3

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?