Escaping Strict Saddle Points of the Moreau Envelope in Nonsmooth Optimization
From MaRDI portal
Publication:5097019
DOI10.1137/21M1430868MaRDI QIDQ5097019
Mateo Díaz, Damek Davis, Dmitriy Drusvyatskiy
Publication date: 19 August 2022
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2106.09815
Numerical mathematical programming methods (65K05) Large-scale problems in mathematical programming (90C06) Nonlinear programming (90C30) Numerical optimization and variational techniques (65K10) Nonsmooth analysis (49J52) Stochastic programming (90C15)
Cites Work
- A trust region algorithm with a worst-case iteration complexity of \(\mathcal{O}(\epsilon ^{-3/2})\) for nonconvex optimization
- Nonconvergence to unstable points in urn models and stochastic approximations
- Introductory lectures on convex optimization. A basic course.
- Convex analysis and nonlinear optimization. Theory and examples
- A geometric analysis of phase retrieval
- Adaptive regularization with cubics on manifolds
- Proximal methods avoid active strict saddles of weakly convex functions
- Finding second-order stationary points in constrained minimization: a feasible direction approach
- A Newton-CG algorithm with complexity guarantees for smooth unconstrained optimization
- First-order methods almost always avoid strict saddle points
- Cubic regularization of Newton method and its global performance
- Generic Minimizing Behavior in Semialgebraic Optimization
- Future Challenges for Variational Analysis
- A model algorithm for composite nondifferentiable optimization problems
- Practical Aspects of the Moreau--Yosida Regularization: Theoretical Preliminaries
- Variational Analysis
- Accelerated Methods for NonConvex Optimization
- Stochastic Model-Based Minimization of Weakly Convex Functions
- Complexity Analysis of Second-Order Line-Search Algorithms for Smooth Nonconvex Optimization
- The Global Optimization Geometry of Low-Rank Matrix Optimization
- A log-barrier Newton-CG method for bound constrained optimization with complexity guarantees
- Finding approximate local minima faster than gradient descent
- On Nonconvex Optimization for Machine Learning
- Inequalities for Gamma Function Ratios
- Limiting subhessians, limiting subjets and their calculus
- Trust-Region Newton-CG with Strong Second-Order Complexity Guarantees for Nonconvex Optimization
This page was built for publication: Escaping Strict Saddle Points of the Moreau Envelope in Nonsmooth Optimization
