hypothesis class
This refers to the set of possible models or functions that a learning algorithm can consider when making predictions. In AI, selecting an appropriate hypothesis class is crucial for effective learning and generalization.
- Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
- Computable universal online learning
- Dimension-free Score Matching and Time Bootstrapping for Diffusion Models
- From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
- How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
- Learning from Interval Targets
- Marginal-Nonuniform PAC Learnability
- Optimal kernel regression bounds under energy-bounded noise