Kurdyka-Łojasiewicz exponent via Hadamard parametrization

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Proximal alternating linearized minimization for nonconvex and nonsmooth problems
Lectures on convex optimization
On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
Semianalytic and subanalytic sets
Geometry of subanalytic and semialgebraic sets
Lasso, fractional norm and structured sparse estimation using a Hadamard product parametrization
From error bounds to the complexity of first-order descent methods for convex functions
A unified approach to error bounds for structured convex optimization problems
Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
First-order methods almost always avoid strict saddle points
The equivalence of three types of error bounds for weakly and approximately convex functions
Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
Clarke Subgradients of Stratifiable Functions
Decoding by Linear Programming
Two Models of Double Descent for Weak Features
Reconciling modern machine-learning practice and the classical bias–variance trade-off
Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods
An Introduction to Differential Manifolds
The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
Stable signal recovery from incomplete and inaccurate measurements
Convex Analysis
Penalty Methods for a Class of Non-Lipschitz Optimization Problems
High-dimensional linear regression via implicit regularization
Convex analysis and monotone operator theory in Hilbert spaces
Smooth over-parameterized solvers for non-smooth structured optimization
More is Less: Inducing Sparsity via Overparameterization
Gradient descent provably escapes saddle points in the training of shallow ReLU networks

This page was built for publication: Kurdyka-Łojasiewicz exponent via Hadamard parametrization