diff --git a/README.md b/README.md
index 2c4249b15cb74ea384e667fa36e0bc966ff752b3..a432a085a886f56a5ba4f07c02cb1d6d97785a4e 100644
--- a/README.md
+++ b/README.md
@@ -92,6 +92,22 @@ https://proceedings.neurips.cc/paper/2021/hash/f197002b9a0853eca5e046d9ca4663d5-
  https://arxiv.org/abs/2302.01629
 
 
+### Additional papers for the interested reader (not covered in course)
+
+- High-dimensional analysis of double descent for linear regression with random projections
+ https://arxiv.org/abs/2303.01372 
+- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
+https://arxiv.org/abs/2302.00257
+- Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression
+https://arxiv.org/abs/2302.00257
+- Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization
+https://arxiv.org/abs/2303.01462
+- Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
+https://arxiv.org/abs/1902.06720
+- Width and Depth Limits Commute in Residual Networks
+https://arxiv.org/abs/2302.00453
+
+
 
 
 ## Credits