Seonglae ChoInherent interpretability
- Linear model
- Decision tree model
Simplex
Interpretable by Design - Constraint Sets with Disjoint Limit Points — LessWrong
cart;horse: How can we constrain our models to be interpretable? Convex, linear sets make for more interpretable parameter spaces, and the simplex an…
https://www.lesswrong.com/posts/kjL9req2p79nSNe5H/interpretable-by-design-constraint-sets-with-disjoint-limit
backpack model
arxiv.org
https://arxiv.org/pdf/2305.16765
Eigenvector analysis through Orthogonalization, Diagonalization, and Truncation, utilizing Category Theory's Monoidal category and String diagram as the language for design and analysis
arxiv.org
https://arxiv.org/pdf/2504.02667