active learning
A machine learning paradigm in which a model selects the most informative data points to learn from, aiming to maximize learning efficiency while minimizing label acquisition costs.
- A Plug-and-Play Query Synthesis Active Learning Framework for Neural PDE Solvers
- Active Seriation: Efficient Ordering Recovery with Statistical Guarantees
- Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling
- Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
- Efficient Training of Minimal and Maximal Low-Rank Recurrent Neural Networks
- Enhancing Deep Batch Active Learning for Regression with Imperfect Data Guided Selection
- Epistemic Uncertainty Estimation in Regression Ensemble Models with Pairwise Epistemic Estimators
- Informed Initialization for Bayesian Optimization and Active Learning
- Near-Exponential Savings for Population Mean Estimation with Active Learning
- ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
- Program Synthesis via Test-Time Transduction
- Reinforced Active Learning for Large-Scale Virtual Screening with Learnable Policy Model
- The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning