Negative Curvature Methods with High-Probability Complexity Guarantees for Stochastic Nonconvex Optimization

Documenti analoghi

• Exploiting Negative Curvature in Conjunction with Adaptive Sampling: Theoretical Results and a Practical Algorithm
  di: Berahas, Albert S., et al.
  Pubblicazione: (2024)
• Modified Line Search Sequential Quadratic Methods for Equality-Constrained Optimization with Unified Global and Local Convergence Guarantees
  di: Berahas, Albert S., et al.
  Pubblicazione: (2024)
• On the Convergence and Complexity of the Stochastic Central Finite-Difference Based Gradient Estimation Methods
  di: Bollapragada, Raghu, et al.
  Pubblicazione: (2025)
• Retrospective Approximation Sequential Quadratic Programming for Stochastic Optimization with General Deterministic Nonlinear Constraints
  di: Berahas, Albert S., et al.
  Pubblicazione: (2025)
• A Sequential Quadratic Programming Method with High Probability Complexity Bounds for Nonlinear Equality Constrained Stochastic Optimization
  di: Berahas, Albert S., et al.
  Pubblicazione: (2023)