learnability
The ability of a learning algorithm or model to effectively generalize from training data to new, unseen data, encompassing aspects of model performance and theoretical properties.
- A learnability analysis on neuro-symbolic learning
- Bounds on the computational complexity of neurons due to dendritic morphology
- Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning
- Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix
- How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
- How Patterns Dictate Learnability in Sequential Data
- LILO: Learning to Reason at the Frontier of Learnability
- Learning Linear Attention in Polynomial Time
- Non-Uniform Multiclass Learning with Bandit Feedback
- The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
- Transformers Learn Faster with Semantic Focus