Pathological subgradient dynamics
From MaRDI portal
Abstract: We construct examples of Lipschitz continuous functions, with pathological subgradient dynamics both in continuous and discrete time. In both settings, the iterates generate bounded trajectories, and yet fail to detect any (generalized) critical points of the function.
Recommendations
- Examples of Pathological Dynamics of the Subgradient Method for Lipschitz Path-Differentiable Functions
- Generalized gradients and paths of descent
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- scientific article; zbMATH DE number 2064529
- Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
Cites work
- scientific article; zbMATH DE number 5348356 (Why is no real title available?)
- scientific article; zbMATH DE number 3675226 (Why is no real title available?)
- scientific article; zbMATH DE number 1254166 (Why is no real title available?)
- scientific article; zbMATH DE number 3805870 (Why is no real title available?)
- scientific article; zbMATH DE number 3295102 (Why is no real title available?)
- scientific article; zbMATH DE number 3398324 (Why is no real title available?)
- A Robust Gradient Sampling Algorithm for Nonsmooth, Nonconvex Optimization
- Amenable functions in optimization
- An Invitation to Tame Optimization
- Analysis of recursive stochastic algorithms
- Asymptotic convergence of nonlinear contraction semigroups in Hilbert space
- Clarke Subgradients of Stratifiable Functions
- Clarke's tangent cones and the boundaries of closed sets in Rn
- Generic Differentiability of Lipschitzian Functions
- Highly irregular separated nets
- Lineability and spaceability of sets of functions on $\mathbb {R}$
- Lineability criteria, with applications
- Linear structure of functions with maximal Clarke subdifferential
- Linear subsets of nonlinear sets in topological vector spaces
- Lipschitz functions with maximal Clarke subdifferentials are generic
- Lipschitz functions with prescribed derivatives and subderivatives
- Lipschitz functions with unexpectedly large sets of nondifferentiability points
- Prox-regular functions in variational analysis
- Random gradient-free minimization of convex functions
- Semismooth and Semiconvex Functions in Constrained Optimization
- Sets Which Split Families of Measurable Sets
- Solution of nonconvex nonsmooth stochastic optimization problems
- Some results and open questions on spaceability in function spaces
- Stochastic Approximations and Differential Inclusions
- Stochastic Approximations and Differential Inclusions, Part II: Applications
- Stochastic Methods for Composite and Weakly Convex Optimization Problems
- Stochastic subgradient method converges on tame functions
- The Minimization of Semicontinuous Functions: Mollifier Subgradients
Cited in
(11)- Piecewise structure of Lyapunov functions and densely checked decrease conditions for hybrid systems
- Pathological dynamical system with constraints.
- Characterization of Filippov representable maps and Clarke subdifferentials
- Examples of Pathological Dynamics of the Subgradient Method for Lipschitz Path-Differentiable Functions
- Certifying the Absence of Spurious Local Minima at Infinity
- Global stability of first-order methods for coercive tame functions
- No dimension-free deterministic algorithm computes approximate stationarities of Lipschitzians
- Conservative and semismooth derivatives are equivalent for semialgebraic maps
- All convex bodies are in the subdifferential of some everywhere differentiable locally Lipschitz function
- Geometric and computational hardness of bilevel programming
- Long term dynamics of the subgradient method for Lipschitz path differentiable functions
This page was built for publication: Pathological subgradient dynamics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5110559)
