predictive performance
A measure of how well a model can predict outcomes based on new, unseen data. It is essential for assessing the effectiveness of AI models in real-world applications and is evaluated using metrics such as accuracy, precision, and recall.
- An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation
- Causal Explanation-Guided Learning for Organ Allocation
- Conformal Information Pursuit for Interactively Guiding Large Language Models
- Credal Prediction based on Relative Likelihood
- DeepHalo: A Neural Choice Model with Controllable Context Effects
- Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
- Distance-informed Neural Processes
- Do-PFN: In-Context Learning for Causal Effect Estimation
- From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models
- Fréchet Geodesic Boosting
- GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
- Generating Computational Cognitive models using Large Language Models
- Monitoring Risks in Test-Time Adaptation
- Neural Rule Lists: Learning Discretizations, Rules, and Order in One Go
- On Group Sufficiency Under Label Bias
- On Logic-based Self-Explainable Graph Neural Networks
- PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions
- Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning
- Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
- QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification
- Quantifying Uncertainty in the Presence of Distribution Shifts
- Selective Learning for Deep Time Series Forecasting