optimization theory
Optimization theory provides the mathematical underpinnings for finding optimal solutions in various contexts, such as minimizing loss functions in machine learning. A strong grasp of optimization theory is essential for developing effective training algorithms and improving model performance.
- Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance
- Constrained Optimization From a Control Perspective via Feedback Linearization
- Local Curvature Descent: Squeezing More Curvature out of Standard and Polyak Gradient Descent
- Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$
- Zeroth-Order Optimization Finds Flat Minima