[DOC] Add link to arXiv submission

README.md

@@ -2,7 +2,7 @@
 
 This package contains the official PyTorch implementation of our
 **memory-efficient and numerically stable KFAC** variant, termed SINGD
-([paper](TODO Insert arXiv link)).
+([paper](http://arxiv.org/abs/2312.05705)).
 
 The main feature is a `torch.optim.Optimizer` which works like most PyTorch optimizers and is compatible with:
 

docs/examples/example_05_structures.py

@@ -26,8 +26,8 @@
 # [`structures`](https://readthedocs.org/projects/singd/api/). The first entry
 # specifies the structure of $\mathbf{K}$ and its momentum
 # $\mathbf{m}_\mathbf{K}$, while the second entry specifies the structure of
-# $\mathbf{C}$ and its momentum $\mathbf{m}_\mathbf{C}$ (see the [paper](TODO
-# Insert link to arXiv submission) for details). It is even possible to specify
+# $\mathbf{C}$ and its momentum $\mathbf{m}_\mathbf{C}$ (see the
+# [paper](http://arxiv.org/abs/2312.05705) for details). It is even possible to specify
 # structures on a per-layer basis (see
 # [this](https://singd.readthedocs.io/en/latest/generated/gallery/example_03_param_groups/)
 # example).

singd/optim/optimizer.py

@@ -26,7 +26,7 @@
 class SINGD(Optimizer):
     """Structured inverse-free natural gradient descent.
 
-    The algorithm is introduced in [this paper](TODO Insert arXiv link) and
+    The algorithm is introduced in [this paper](http://arxiv.org/abs/2312.05705) and
     extends the inverse-free KFAC algorithm from [Lin et al. (ICML
     2023)](https://arxiv.org/abs/2302.09738) with structured pre-conditioner
     matrices.
@@ -104,8 +104,8 @@ def __init__(
     ):  # noqa: D301
         """Structured inverse-free natural gradient descent optimizer.
 
-        Uses the empirical Fisher. See the [paper](TODO Insert arXiv link) for the
-        notation.
+        Uses the empirical Fisher. See the [paper](http://arxiv.org/abs/2312.05705) for
+        the notation.
 
         Args:
             model: The neural network whose parameters (or a subset thereof) will be