Newton-type methods for non-convex optimization under inexact Hessian information
Published 2019 View Full Article
- Home
- Publications
- Publication Search
- Publication Details
Title
Newton-type methods for non-convex optimization under inexact Hessian information
Authors
Keywords
-
Journal
MATHEMATICAL PROGRAMMING
Volume -, Issue -, Pages -
Publisher
Springer Science and Business Media LLC
Online
2019-05-23
DOI
10.1007/s10107-019-01405-z
References
Ask authors/readers for more resources
Related references
Note: Only part of the references are listed.- Sub-sampled Newton methods
- (2018) Farbod Roosta-Khorasani et al. MATHEMATICAL PROGRAMMING
- Complexity and global rates of trust-region methods based on probabilistic models
- (2017) Serge Gratton et al. IMA JOURNAL OF NUMERICAL ANALYSIS
- Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
- (2017) C. Cartis et al. MATHEMATICAL PROGRAMMING
- RandNLA
- (2016) Petros Drineas et al. COMMUNICATIONS OF THE ACM
- Stochastic derivative-free optimization using a trust region framework
- (2016) Jeffrey Larson et al. COMPUTATIONAL OPTIMIZATION AND APPLICATIONS
- A trust region algorithm with a worst-case iteration complexity of $$\mathcal{O}(\epsilon ^{-3/2})$$ O ( ϵ - 3 / 2 ) for nonconvex optimization
- (2016) Frank E. Curtis et al. MATHEMATICAL PROGRAMMING
- On the worst-case complexity of nonlinear stepsize control algorithms for convex unconstrained optimization
- (2016) G.N. Grapiglia et al. OPTIMIZATION METHODS & SOFTWARE
- A linear-time algorithm for trust region problems
- (2015) Elad Hazan et al. MATHEMATICAL PROGRAMMING
- Assessing Stochastic Algorithms for Large Scale Nonlinear Least Squares Problems Using Extremal Probabilities of Linear Combinations of Gamma Random Variables
- (2015) Farbod Roosta-Khorasani et al. SIAM-ASA Journal on Uncertainty Quantification
- On the use of iterative methods in cubic regularization for unconstrained optimization
- (2014) Tommaso Bianconcini et al. COMPUTATIONAL OPTIMIZATION AND APPLICATIONS
- Convergence of Trust-Region Methods Based on Probabilistic Models
- (2014) A. S. Bandeira et al. SIAM JOURNAL ON OPTIMIZATION
- Stochastic Algorithms for Inverse Problems Involving PDEs and many Measurements
- (2014) Farbod Roosta-Khorasani et al. SIAM JOURNAL ON SCIENTIFIC COMPUTING
- User-Friendly Tail Bounds for Sums of Random Matrices
- (2011) Joel A. Tropp FOUNDATIONS OF COMPUTATIONAL MATHEMATICS
- Complexity bounds for second-order optimality in unconstrained optimization
- (2011) C. Cartis et al. JOURNAL OF COMPLEXITY
- Evaluation complexity of adaptive cubic regularization methods for convex unconstrained optimization
- (2011) Coralia Cartis et al. OPTIMIZATION METHODS & SOFTWARE
- Adaptive cubic regularisation methods for unconstrained optimization. Part II: worst-case function- and derivative-evaluation complexity
- (2010) Coralia Cartis et al. MATHEMATICAL PROGRAMMING
- On the Complexity of Steepest Descent, Newton's and Regularized Newton's Methods for Nonconvex Unconstrained Optimization Problems
- (2010) C. Cartis et al. SIAM JOURNAL ON OPTIMIZATION
- Adaptive cubic regularisation methods for unconstrained optimization. Part I: motivation, convergence and numerical results
- (2009) Coralia Cartis et al. MATHEMATICAL PROGRAMMING
- Global Convergence of General Derivative-Free Trust-Region Algorithms to First- and Second-Order Critical Points
- (2009) Andrew R. Conn et al. SIAM JOURNAL ON OPTIMIZATION
- Iterative Methods for Finding a Trust-region Step
- (2009) Jennifer B. Erway et al. SIAM JOURNAL ON OPTIMIZATION
- A recursive Formula-trust-region method for bound-constrained nonlinear optimization
- (2008) S. Gratton et al. IMA JOURNAL OF NUMERICAL ANALYSIS
- Recursive Trust-Region Methods for Multiscale Nonlinear Optimization
- (2008) Serge Gratton et al. SIAM JOURNAL ON OPTIMIZATION
Find Funding. Review Successful Grants.
Explore over 25,000 new funding opportunities and over 6,000,000 successful grants.
ExplorePublish scientific posters with Peeref
Peeref publishes scientific posters from all research disciplines. Our Diamond Open Access policy means free access to content and no publication fees for authors.
Learn More