List of resouces for the advanced topics in data science. The list comprises of resources I found usefull or interesting during my work.
Statistical physics-inspired approach to deep learning theory: https://arxiv.org/pdf/2004.09280.pdf.
Effective theory of deep learning: https://arxiv.org/pdf/2106.10165.pdf.
Implicit gradient regularization: https://proceedings.mlr.press/v162/zhao22i/zhao22i.pdf.
Gradient regularization: https://arxiv.org/pdf/1712.09936.pdf.
Gradient reversal layer: https://arxiv.org/pdf/1409.7495.pdf.
One epoch overfitting phenomenon: https://arxiv.org/pdf/2305.19531.pdf, https://arxiv.org/pdf/2209.06053.pdf.
https://arxiv.org/pdf/2101.02342.pdf
https://www.kaggle.com/code/headsortails/hidden-gems-a-collection-of-underrated-notebooks
Guide to variational inference: https://arxiv.org/pdf/2103.01327.pdf.
https://bookdown.org/max/FES/.
Infrastructure: https://fullstackdeeplearning.com/spring2021/lecture-6/.
https://christophm.github.io/interpretable-ml-book/.
http://www.datascienceassn.org/sites/default/files/Topological%20Data%20Analysis.pdf.
Paper: https://arxiv.org/pdf/1802.03426.pdf. Library: https://umap-learn.readthedocs.io/en/latest/.