Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Balanced Active Inference
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes balanced active inference, an active-inference method for estimation under a limited labeling budget that uses balanced (non-independent) sampling to make fuller use of available information and improve statistical efficiency over independent-sampling approaches.
Problem
Labeling budgets are limited in data-driven research (medical analysis, remote sensing, population census), and prior active inference methods based on independent sampling use available information insufficiently, hurting statistical efficiency.
Approach
Replaces independent sampling in active inference with a balanced sampling scheme that exploits the available unlabeled information more fully, improving statistical efficiency over uniform and independent active sampling.
Experimental setup
Baselines: uniform sampling independent sampling active inference
Builds on: active inference
Closest papers by meaning
- Robust Sampling for Active Statistical Inference (NeurIPS 2025 · similarity 0.88)
- Active Statistical Inference (ICML 2024 · similarity 0.87)
- Uncertainty Herding: One Active Learning Method for All Label Budgets (ICLR 2025 · similarity 0.85)
- Uncertainty for Active Learning on Graphs (ICML 2024 · similarity 0.84)
- Post-ADC Inference: Valid Inference After Active Data Collection (NeurIPS 2026 · similarity 0.82)
- Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity (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.