style: fix citation style

Author: Nimrais

docs/src/references.bib

@@ -5,12 +5,6 @@
 % --- A
 %
 %
-@article{DoddSharrockNemeth:2024,
-  title={Learning-rate-free stochastic optimization over Riemannian manifolds},
-  author={Dodd, Daniel and Sharrock, Louis and Nemeth, Christopher},
-  journal={arXiv preprint arXiv:2406.02296},
-  year={2024}
-}
 
 @book{AbsilMahonySepulchre:2008,
     AUTHOR    = {Absil, P.-A. and Mahony, R. and Sepulchre, R.},
@@ -294,6 +288,7 @@ @techreport{deCasteljau:1963
     YEAR      = {1963}
 }
 
+
 @article{ChambollePock:2011,
     AUTHOR       = {Chambolle, Antonin and Pock, Thomas},
     YEAR         = {2011},
@@ -344,6 +339,7 @@ @article{DaiYuan:1999
     VOLUME    = {10},
     YEAR      = {1999}
 }
+
 @article{DiepeveenLellmann:2021,
     AUTHOR     = {Willem Diepeveen and Jan Lellmann},
     DOI        = {10.1137/21m1398513},
@@ -358,13 +354,22 @@ @article{DiepeveenLellmann:2021
     VOLUME     = {14},
     YEAR       = {2021},
 }
+
+@article{DoddSharrockNemeth:2024,
+  title={Learning-rate-free stochastic optimization over Riemannian manifolds},
+  author={Dodd, Daniel and Sharrock, Louis and Nemeth, Christopher},
+  journal={arXiv preprint arXiv:2406.02296},
+  year={2024}
+}
+
 @techreport{Dreisigmeyer:2007,
     AUTHOR = {Dreisigmeyer, David W.},
     INSTITUTION = {Optimization Online},
     TITLE = {Direct Search Alogirthms over Riemannian Manifolds},
     URL = {https://optimization-online.org/?p=9134},
     YEAR = {2007}
 }
+
 @article{DuranMoelleSbertCremers:2016,
     AUTHOR   = {Duran, J. and Moeller, M. and Sbert, C. and Cremers, D.},
     TITLE    = {Collaborative Total Variation: A General Framework for Vectorial TV Models},

src/plans/stepsize.jl

@@ -1692,7 +1692,7 @@ end
     DistanceOverGradientsStepsize{R<:Real} <: Stepsize
 
 Implements the Riemannian Distance over Gradients (RDoG) stepsize schedule, a learning-rate-free 
-optimization method for Riemannian manifolds introduced by [@dodd2024learning].
+optimization method for Riemannian manifolds introduced by [DoddSharrockNemeth:2024].
 
 This stepsize adapts automatically without hyperparameter tuning by tracking the maximum distance 
 from the initial point and accumulating gradient norms.