theoretical foundation
The underlying principles, mathematical structures, and theoretical concepts that form the basis of various algorithms and models in AI, providing insights into their validity and performance.
- A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
- Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
- Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
- High-Order Flow Matching: Unified Framework and Sharp Statistical Rates
- Linear Mixture Distributionally Robust Markov Decision Processes
- MAP Estimation with Denoisers: Convergence Rates and Guarantees
- Spectral Analysis of Diffusion Models with Application to Schedule Design