linear convergence rate
Linear convergence rate describes the rate at which an algorithm approaches an optimal solution, characterized by a consistent reduction in error per iteration. In AI optimization, faster convergence rates can lead to more efficient training and improved model performance.
- A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization
- Accelerating Model-Free Optimization via Averaging of Cost Samples
- An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks
- Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
- Non-Convex Tensor Recovery from Tube-Wise Sensing