theoretical foundations
The underlying mathematical and statistical principles that provide a formal framework for understanding and analyzing AI algorithms and methods.
- Concentration and excess risk bounds for imbalanced classification with synthetic oversampling
- Constrained Optimization From a Control Perspective via Feedback Linearization
- Faster Fixed-Point Methods for Multichain MDPs
- Generalization Bounds for Model-based Algorithm Configuration
- On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
- On the Sample Complexity Bounds of Bilevel Reinforcement Learning
- Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality
- State Size Independent Statistical Error Bound for Discrete Diffusion Models
- Stepsize anything: A unified learning rate schedule for budgeted-iteration training
- Towards Multi-Table Learning: A Novel Paradigm for Complementarity Quantification and Integration
- When majority rules, minority loses: bias amplification of gradient descent
- Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework