Research map / Learning theory and algorithms / Prediction and decision losses
On the Computation of Necessary and Sufficient Explanations
Adnan Darwiche, Chunxi Ji
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 SNR instead of NR to enumerate shortest necessary reasons | decision-tree and decision-graph benchmarks · 15 benchmarks | running time | Improved |
| Use SSR instead of SR to enumerate shortest sufficient reasons | decision-tree and decision-graph benchmarks · 15 benchmarks | running time | Improved |
| Use SNR instead of NR | fash-mnist · fash-mnist | running time (s): 0.0123 -> 0.0008 | Improved |
| Use SNR instead of NR | gisette · gisette | running time (s): 0.0013 -> 0.0004 | Improved |
| Use SNR instead of NR | mnist-784 · mnist-784 | running time (s): 0.0099 -> 0.0008 | Improved |
| Use SNR instead of NR | mooring · mooring | running time (s): 0.7678 -> 0.0189 | Improved |
| Use SSR instead of SR | shortest sufficient reason enumeration · 15 benchmarks | timeouts: 2222 -> 37 | Improved |
| Use NR instead of SNR | decision-tree benchmarks · decision trees | timeouts: 19 | Mixed |
Closest papers by meaning
- On Computing Probabilistic Explanations for Decision Trees (NeurIPS 2022 · similarity 0.89)
- Sufficient Reasons for Classifier Decisions in the Presence of Domain Constraints (AAAI 2022 · similarity 0.86)
- Probabilistic Explanations for Linear Models (AAAI 2025 · similarity 0.85)
- From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal Hierarchy (ICLR 2025 · similarity 0.82)
- Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms (ICML 2025 · similarity 0.82)
- Delivering Inflated Explanations (AAAI 2024 · similarity 0.82)
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.
