Escaping saddle points in distributed nonconvex optimization via cubic regularization
From MaRDI portal
Cites work
- A Newton-based method for nonconvex optimization with fast evasion of saddle points
- A Newton-CG Based Barrier Method for Finding a Second-Order Stationary Point of Nonconvex Conic Optimization with Complexity Guarantees
- Adaptive cubic regularization methods with dynamic inexact Hessian information and applications to finite-sum minimization
- Broadcast-based asynchronous convex optimization using quantized distributed stochastic mirror descent algorithm
- Communication-efficient distributed cubic Newton with compressed lazy Hessian
- Compressed gradient tracking algorithms for distributed nonconvex optimization
- Convergence rates for the heavy-ball continuous dynamics for non-convex optimization, under Polyak-Łojasiewicz condition
- Cubic regularization of Newton method and its global performance
- DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization
- Differentially private and communication-efficient distributed nonconvex optimization algorithms
- Distributed adaptive Newton methods with global superlinear convergence
- Distributed Control of Multiconsensus
- Distributed Control of Networked Dynamical Systems: Static Feedback, Integral Action and Consensus
- Distributed nonconvex constrained optimization over time-varying digraphs
- Distributed Stochastic Consensus Optimization With Momentum for Nonconvex Nonsmooth Problems
- Fast decentralized nonconvex finite-sum optimization with recursive variance reduction
- Fast linear iterations for distributed averaging
- Fully distributed constrained optimization algorithm over unbalanced network and its application to smart grids
- Lectures on convex optimization
- Linear Convergence of First- and Zeroth-Order Primal–Dual Algorithms for Distributed Nonconvex Optimization
- Local consensus based multi-objective distributed optimization and its application
- Low rank approximation. Algorithms, implementation, applications
- Newton-type methods for non-convex optimization under inexact Hessian information
- On the complexity of steepest descent, Newton's and regularized Newton's methods for nonconvex unconstrained optimization problems
- Optimization by simulated annealing
- Push–Pull Gradient Methods for Distributed Optimization in Networks
- Random Geometric Graphs
- Regularized Newton Method with Global \({\boldsymbol{\mathcal{O}(1/{k}^2)}}\) Convergence
- Second-order guarantees of distributed gradient algorithms
- Solving Large-Scale Cubic Regularization by a Generalized Eigenvalue Problem
This page was built for publication: Escaping saddle points in distributed nonconvex optimization via cubic regularization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7355304)
