stationary points
- Block Coordinate Descent for Neural Networks Provably Finds Global Minima
- Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
- Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
- Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds
- The Adaptive Complexity of Minimizing Relative Fisher Information
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
- Theoretical Investigation of Adafactor for Non-Convex Smooth Optimization