Research map / Learning theory and algorithms / Prediction and decision losses
Model Interpretability through the lens of Computational Complexity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use FBDDs instead of MLPs | Local post-hoc explainability queries · MCR | computational complexity | Helped |
| Use FBDDs instead of MLPs | Local post-hoc explainability queries · MSR | computational complexity | Helped |
| Use FBDDs instead of MLPs | Local post-hoc explainability queries · CSR | computational complexity | Helped |
| Use FBDDs instead of MLPs | Local post-hoc explainability queries · CC | computational complexity | Helped |
| Use perceptrons instead of MLPs | Local post-hoc explainability queries · MCR | computational complexity | Helped |
| Use perceptrons instead of MLPs | Local post-hoc explainability queries · MSR | computational complexity | Helped |
| Use perceptrons instead of MLPs | Local post-hoc explainability queries · CSR | computational complexity | Helped |
| Use perceptrons instead of MLPs | Local post-hoc explainability queries · CC | computational complexity | No clear effect |
| Use perceptrons instead of FBDDs | Local post-hoc explainability queries · MSR | computational complexity | Helped |
| Use FBDDs instead of perceptrons | Local post-hoc explainability queries · CC | computational complexity | Helped |
| Use an FPRAS for counting completions with perceptrons rather than MLPs | CountCompletions · Perceptrons versus MLPs | approximation tractability | Helped |
| Restrict perceptron weights and biases to unary-encoded integers | Perceptron CountCompletions · CC | computational complexity | Helped |
Closest papers by meaning
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.93)
- Additive Models Explained: A Computational Complexity Approach (NeurIPS 2025 · similarity 0.90)
- What makes an Ensemble (Un) Interpretable? (ICML 2025 · similarity 0.89)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.88)
- The Computational Complexity of Circuit Discovery for Inner Interpretability (ICLR 2025 · similarity 0.88)
- Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable? (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.