Inertial Newton algorithms avoiding strict saddle points (Q6145046): Difference between revisions

From MaRDI portal
Added link to MaRDI item.
ReferenceBot (talk | contribs)
Changed an Item
Property / cites work
 
Property / cites work: A gradient-type algorithm with backward inertial steps associated to a nonconvex minimization problem / rank
 
Normal rank
Property / cites work
 
Property / cites work: An extension of the second order dynamical system that models Nesterov's convex gradient method / rank
 
Normal rank
Property / cites work
 
Property / cites work: A second-order gradient-like dissipative dynamical system with Hessian-driven damping. Application to optimization and mechanics. / rank
 
Normal rank
Property / cites work
 
Property / cites work: Limit Points of Sequences in Metric Spaces / rank
 
Normal rank
Property / cites work
 
Property / cites work: Newton-like Inertial Dynamics and Proximal Algorithms Governed by Maximally Monotone Operators / rank
 
Normal rank
Property / cites work
 
Property / cites work: Continuous Newton-like inertial dynamics for monotone inclusions / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q2761421 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods / rank
 
Normal rank
Property / cites work
 
Property / cites work: A Dynamical Approach to an Inertial Forward-Backward Algorithm for Convex Minimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Fast convex optimization via inertial dynamics with Hessian driven damping / rank
 
Normal rank
Property / cites work
 
Property / cites work: Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity / rank
 
Normal rank
Property / cites work
 
Property / cites work: Rate of convergence of the Nesterov accelerated gradient method in the subcritical case <i>α</i> ≤ 3 / rank
 
Normal rank
Property / cites work
 
Property / cites work: First-order optimization algorithms via inertial systems with Hessian driven damping / rank
 
Normal rank
Property / cites work
 
Property / cites work: Fast optimization via inertial dynamics with closed-loop damping / rank
 
Normal rank
Property / cites work
 
Property / cites work: Optimal Convergence Rates for Nesterov Acceleration / rank
 
Normal rank
Property / cites work
 
Property / cites work: A New Value Iteration method for the Average Cost Dynamic Programming Problem / rank
 
Normal rank
Property / cites work
 
Property / cites work: An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions / rank
 
Normal rank
Property / cites work
 
Property / cites work: Tikhonov regularization of a second order dynamical system with Hessian driven damping / rank
 
Normal rank
Property / cites work
 
Property / cites work: An Inertial Newton Algorithm for Deep Learning / rank
 
Normal rank
Property / cites work
 
Property / cites work: The gradient and heavy ball with friction dynamical systems: The quasiconvex case / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3282146 / rank
 
Normal rank
Property / cites work
 
Property / cites work: A Lemma in the Theory of Structural Stability of Differential Equations / rank
 
Normal rank
Property / cites work
 
Property / cites work: The stable, center-stable, center, center-unstable, unstable manifolds / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4064160 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5491447 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Local convergence of the heavy-ball method and iPiano for non-convex optimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Behavior of accelerated gradient methods near critical points of nonconvex functions / rank
 
Normal rank
Property / cites work
 
Property / cites work: A generalization of Hartman's linearization theorem / rank
 
Normal rank
Property / cites work
 
Property / cites work: Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3997917 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Some methods of speeding up the convergence of iteration methods / rank
 
Normal rank
Property / cites work
 
Property / cites work: Understanding the acceleration phenomenon via high-resolution differential equations / rank
 
Normal rank
Property / cites work
 
Property / cites work: Convergence rates for an inertial algorithm of gradient type associated to a smooth non-convex minimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Backtracking gradient descent method and some applications in large scale optimisation. II: Algorithms and experiments / rank
 
Normal rank
Property / cites work
 
Property / cites work: The Differential Inclusion Modeling FISTA Algorithm and Optimality of Convergence Rate in the Case b $\leq3$ / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5340295 / rank
 
Normal rank

Revision as of 11:43, 22 August 2024

scientific article; zbMATH DE number 7785178
Language Label Description Also known as
English
Inertial Newton algorithms avoiding strict saddle points
scientific article; zbMATH DE number 7785178

    Statements

    Inertial Newton algorithms avoiding strict saddle points (English)
    0 references
    0 references
    8 January 2024
    0 references
    non-convex optimization
    0 references
    algorithms for machine learning
    0 references
    dynamical systems
    0 references
    convergence analysis
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references

    Identifiers