Research map / Probabilistic and scientific modeling / Molecules and proteins
A Theory of Usable Information under Computational Constraints
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 predictive F-information instead of Shannon mutual-information estimators for Chow-Liu tree learning | F-information(Gaussian) and F-information(Logistic) · Synthetic continuous high-dimensional tree structure learning | wrong-edges ratio | Helped |
| Use F-information(Gaussian) for Chow-Liu tree learning | F-information(Gaussian) · Simulation-A | ground-truth tree recovery | Helped |
| Use predictive F-information instead of non-parametric Shannon mutual-information estimators | Gene regulatory network inference · DREAM5 in-silico dataset | AUC | Helped |
| Use predictive F-information with conditional PixelCNN++ as the predictive family | Moving-MNIST · Stochastic-dynamics video frame ordering | relative frame-order recovery | Helped |
| Use predictive F-information with conditional PixelCNN++ instead of Shannon mutual information | Deterministic-Moving-MNIST · Deterministic-dynamics video frame ordering | frame-order recovery | Helped |
| Use PixelCNN++ predictive F-information at larger frame distances | Deterministic-Moving-MNIST · Frame distances greater than or equal to 9 | frame-order recovery | Mixed |
| Train a fair representation by minimizing F-information against one neural-network attacker family | Fair representation learning · Adult, German, and Heritage | sensitive-attribute information under a different attacker family | Hurt |
Closest papers by meaning
- Information Shapes Koopman Representation (ICLR 2026 · similarity 0.84)
- On Mutual Information Maximization for Representation Learning (ICLR 2020 · similarity 0.84)
- Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning (NeurIPS 2025 · similarity 0.84)
- Entropy and mutual information in models of deep neural networks (NeurIPS 2018 · similarity 0.84)
- An Information Theoretic Perspective on Conformal Prediction (NeurIPS 2024 · similarity 0.83)
- Mutual Information Estimation via $f$-Divergence and Data Derangements (NeurIPS 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.