Kurdyka-Łojasiewicz exponent via Hadamard parametrization
From MaRDI portal
(Redirected from Publication:6663111)
Cites work
- A unified approach to error bounds for structured convex optimization problems
- An introduction to differential manifolds. Translated from the 2nd French edition by Jonathan Upjohn
- Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
- Clarke Subgradients of Stratifiable Functions
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
- Convex Analysis
- Convex analysis and monotone operator theory in Hilbert spaces
- Decoding by Linear Programming
- Error bounds, quadratic growth, and linear convergence of proximal methods
- First-order methods almost always avoid strict saddle points
- From error bounds to the complexity of first-order descent methods for convex functions
- Geometry of subanalytic and semialgebraic sets
- Gradient descent provably escapes saddle points in the training of shallow ReLU networks
- High-dimensional linear regression via implicit regularization
- scientific article; zbMATH DE number 3465694 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 7626727 (Why is no real title available?)
- Lasso, fractional norm and structured sparse estimation using a Hadamard product parametrization
- Lectures on convex optimization
- Linear and nonlinear functional analysis with applications. With 401 problems and 52 figures
- Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
- More is Less: Inducing Sparsity via Overparameterization
- On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
- Penalty methods for a class of non-Lipschitz optimization problems
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Reconciling modern machine-learning practice and the classical bias-variance trade-off
- Semianalytic and subanalytic sets
- Smooth over-parameterized solvers for non-smooth structured optimization
- Stable signal recovery from incomplete and inaccurate measurements
- The equivalence of three types of error bounds for weakly and approximately convex functions
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Two models of double descent for weak features
Cited in
(1)
This page was built for publication: Kurdyka-Łojasiewicz exponent via Hadamard parametrization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6663111)
