Research map / Probabilistic and scientific modeling / Molecules and proteins
Variational Information Pursuit for Interpretable Predictions
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 V-IP instead of the generative approach on RGB-CIFAR images | Information Pursuit · RGB-CIFAR images | accuracy | Helped |
| Use the generative approach instead of V-IP when a good generative model is available | Information Pursuit · MNIST | accuracy | Hurt |
| Use V-IP instead of BSODA | Information Pursuit · SymCAT datasets | accuracy at the same number of queries | Helped |
| Use the greedy V-IP strategy instead of RAM or RAM+ | Sequential interpretable prediction · Numerous datasets across vision, NLP, and medical diagnosis | prediction performance | Helped |
| Remove the initial random sampling phase (ablation) | V-IP · Most datasets in the ablation study | accuracy vs. explanation length trade-off | Helped |
| Remove the initial random sampling phase (ablation) | V-IP · Training compute | training speed | Hurt |
| Use interpretable query sets rather than full-input non-interpretable models | V-IP · Almost all datasets | accuracy | Hurt |
Closest papers by meaning
- Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification (ICLR 2024 · similarity 0.92)
- Conformal Information Pursuit for Interactively Guiding Large Language Models (NeurIPS 2025 · similarity 0.89)
- Information Maximization Perspective of Orthogonal Matching Pursuit with Applications to Explainable AI (NeurIPS 2023 · similarity 0.84)
- Generative Decision Making Under Uncertainty (AAAI 2023 · similarity 0.84)
- Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models (NeurIPS 2025 · similarity 0.84)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · 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.