deel.lip.losses module¶
This module contains losses used in wasserstein distance estimation. See https://arxiv.org/abs/2006.06520 for more information.
-
deel.lip.losses.
HKR_loss
(alpha, min_margin=1)¶ Wasserstein loss with a regularization param based on hinge loss.
\[\inf_{f \in Lip_1(\Omega)} \underset{\textbf{x} \sim P_-}{\mathbb{E}} \left[f(\textbf{x} )\right] - \underset{\textbf{x} \sim P_+} {\mathbb{E}} \left[f(\textbf{x} )\right] + \alpha \underset{\textbf{x}}{\mathbb{E}} \left(\text{min_margin} -Yf(\textbf{x})\right)_+\]- Parameters
alpha – regularization factor
min_margin – minimal margin ( see hinge_margin_loss )
term of the loss. In order to be consistent (Kantorovich-rubinstein) –
hinge and KR (between) –
first label must yield the positve class (the) –
the second yields negative class. (while) –
- Returns
a function that compute the regularized Wasserstein loss
-
deel.lip.losses.
HKR_multiclass_loss
(alpha=0.0, min_margin=1)¶ The multiclass version of HKR. This is done by computing the HKR term over each class and averaging the results.
- Parameters
alpha – regularization factor
min_margin – minimal margin ( see Hinge_multiclass_loss )
- Returns
Callable, the function to compute HKR loss #Note y_true has to be one hot encoded
-
deel.lip.losses.
Hinge_multiclass_loss
(min_margin=1)¶ Loss to estimate the Hinge loss in a multiclass setup. It compute the elementwise hinge term. Note that this formulation differs from the one commonly found in tensorflow/pytorch (with marximise the difference between the two largest logits). This formulation is consistent with the binary classification loss used in a multiclass fashion. Note y_true should be one hot encoded. labels in (1,0)
- Returns
Callable, the function to compute multiclass Hinge loss #Note y_true has to be one hot encoded
-
deel.lip.losses.
KR_loss
()¶ Loss to estimate wasserstein-1 distance using Kantorovich-Rubinstein duality. The Kantorovich-Rubinstein duality is formulated as following:
\[W_1(\mu, \nu) = \sup_{f \in Lip_1(\Omega)} \underset{\textbf{x} \sim \mu}{\mathbb{E}} \left[f(\textbf{x} )\right] - \underset{\textbf{x} \sim \nu}{\mathbb{E}} \left[f(\textbf{x} )\right]\]Where mu and nu stands for the two distributions, the distribution where the label is 1 and the rest.
- Returns
Callable, the function to compute Wasserstein loss
-
deel.lip.losses.
KR_multiclass_loss
()¶ Loss to estimate average of W1 distance using Kantorovich-Rubinstein duality over outputs. Note y_true should be one hot encoding (labels being 1s and 0s ). In this multiclass setup thr KR term is computed for each class and then averaged.
- Returns
Callable, the function to compute Wasserstein multiclass loss. #Note y_true has to be one hot encoded
-
deel.lip.losses.
MultiMarginLoss
(min_margin=1)¶ - Compute the mean hinge margin loss for multi class (equivalent to Pytorch
multi_margin_loss)
- Parameters
min_margin – the minimal margin to enforce.
has to be to_categorical (y_true) –
- Returns
Callable, the function to compute multi margin loss
-
deel.lip.losses.
hinge_margin_loss
(min_margin=1)¶ Compute the hinge margin loss.
\[\underset{\textbf{x}}{\mathbb{E}} \left(\text{min_margin} -Yf(\textbf{x})\right)_+\]- Parameters
min_margin – the minimal margin to enforce.
- Returns
a function that compute the hinge loss.
-
deel.lip.losses.
neg_KR_loss
()¶ Loss to compute the negative wasserstein-1 distance using Kantorovich-Rubinstein duality. This allows the maximisation of the term using conventional optimizer.
- Returns
Callable, the function to compute negative Wasserstein loss