learning theory
Learning theory in AI focuses on understanding the principles and frameworks that govern how models learn from data, including aspects like model capacity, generalization, and the effects of training parameters on performance.
- $O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
- Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
- Learning single index models via harmonic decomposition
- Online Learning of Pure States is as Hard as Mixed States
- Optimal Mistake Bounds for Transductive Online Learning
- Revisiting Agnostic Boosting
- Stackelberg Learning with Outcome-based Payment