On convergence of distributed approximate Newton methods: globalization, sharper bounds and beyond
From MaRDI portal
Publication:5148997
Recommendations
- Distributed adaptive Newton methods with global superlinear convergence
- scientific article; zbMATH DE number 7307473
- Distributed adaptive greedy quasi-Newton methods with explicit non-asymptotic convergence bounds
- Event and Its Application in Algebraic Structures
- A globally convergent incremental Newton method
Cites work
- Catalyst acceleration for first-order convex optimization: from theory to practice
- Communication-efficient distributed statistical inference
- Distributed coordinate descent method for learning with big data
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Distributed optimization with arbitrary local solvers
- Distributed stochastic variance reduced gradient methods by sampling extra data with replacement
- DSCOVR: randomized primal-dual block coordinate algorithms for asynchronous distributed optimization
- scientific article; zbMATH DE number 6982986 (Why is no real title available?)
- Learning kernel-based halfspaces with the 0-1 loss
- SGDLibrary: a MATLAB library for stochastic optimization algorithms
- Some methods of speeding up the convergence of iteration methods
- Stochastic primal-dual coordinate method for regularized empirical risk minimization
- The landscape of empirical risk for nonconvex losses
- User-friendly tail bounds for sums of random matrices
Cited in
(7)- Distributed approximate Newton algorithms and weight design for constrained optimization
- Hyperfast second-order local solvers for efficient statistically preconditioned distributed optimization
- Compression and data similarity: combination of two techniques for communication-efficient solving of distributed variational inequalities
- Distributed adaptive greedy quasi-Newton methods with explicit non-asymptotic convergence bounds
- Adaptive pruning-based Newton's method for distributed learning
- Accelerated stochastic extragradient: mixing Hessian and gradient similarity to reduce communication in distributed and federated learning
- Accelerated double-sketching subspace Newton
This page was built for publication: On convergence of distributed approximate Newton methods: globalization, sharper bounds and beyond
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5148997)
