First- and second-order high probability complexity bounds for trust-region methods with noisy oracles
From MaRDI portal
Publication:6608030
Recommendations
- Trust-region algorithms: probabilistic complexity and intrinsic noise with applications to subsampling techniques
- A trust region method for noisy unconstrained optimization
- Stochastic derivative-free optimization using a trust region framework
- An adaptive trust-region method without function evaluations
- Stochastic optimization using a trust-region method and random models
Cites work
- A stochastic line search method with expected complexity analysis
- Benchmarking Derivative-Free Optimization Algorithms
- Complexity and global rates of trust-region methods based on probabilistic models
- Computation of sparse low degree interpolating polynomials and their application to derivative-free optimization
- Convergence of trust-region methods based on probabilistic models
- Cubic regularization of Newton method and its global performance
- Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods
- Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise
- Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
- High-dimensional probability. An introduction with applications in data science
- Introduction to Derivative-Free Optimization
- On the Global Convergence of Trust Region Algorithms Using Inexact Gradient Information
- On the Lagrange functions of quadratic models that are defined by interpolation*
- Random gradient-free minimization of convex functions
- Recent advances in trust region algorithms
- Sample size selection in optimization methods for machine learning
- Stochastic optimization using a trust-region method and random models
- Trust Region Methods
- UOBYQA: unconstrained optimization by quadratic approximation
Cited in
(4)- Trust-region algorithms: probabilistic complexity and intrinsic noise with applications to subsampling techniques
- A sequential quadratic programming method with high-probability complexity bounds for nonlinear equality-constrained stochastic optimization
- A trust region method for noisy unconstrained optimization
- A non-monotone trust-region method with noisy oracles and additional sampling
This page was built for publication: First- and second-order high probability complexity bounds for trust-region methods with noisy oracles
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6608030)
