Extending `BCEWithLogitsLoss` to non-binary labels

BackPACK's extensions that rely on the probabilistic interpretation of a loss function as a negative log likelihood (quantities based on the Fisher, i.e. `BatchDiagGGNMC`, `DiagGGNMC`, `SqrtGGNMC`, `KFAC`) are limited to binary labels for `BCEWithLogitsLoss`.

This issue serves as documentation for the required steps and problems to support continuous-valued labels.

**Description:** Currently, we assume binary labels $y_n \in \{0; 1\}$. In this case, `BCEWithLogitsLoss` corresponds to the negative log likelihood of a Bernoulli distribution $p(y \mid f_n)$ with $f_{n} \in (0; 1)$ the sigmoid probability.

But `BCEWithLogitsLoss` also supports continuous labels $y_n \in [0; 1]$. In this case, `BCEWithLogitsLoss` corresponds to negative log likelihood of a continuous Bernoulli distribution $p(y \mid f_{n}) \propto f_{n}^{y} (1 - f_n)^{1 - y}$, such that $- \log p(y=y_{n} \mid f_{n}) \propto -y_{n} \log(f_n) - (1 - y_n) \log(1 - f_n)$.

**Implementation:** Depending on the nature of labels (binary or continuous), a different distribution must be used (Bernoulli or continuous Bernoulli) to compute sampled gradients. However, at the moment the `_make_distribution` function does not take into account the labels, but only receives the subsampled inputs. Hence, the interface must be adapted in order to support continuous labels in `BCEWithLogitsLoss`.

**Problems:**
- A problem with that is that this approach would determine at run time, which properties the labels satisfy. If however we're using a data set with non-binary labels, but coincidentally feed a batch with binary labels (or a single sample), then this approach will use the wrong distribution. Not sure how to fix this, other than asking the user for the nature of their data.