SCORE: approximating curvature information under self-concordant regularization
From MaRDI portal
Publication:6051307
DOI10.1007/s10589-023-00502-2arXiv2112.07344OpenAlexW4383618066MaRDI QIDQ6051307
Alberto Bemporad, Adeyemi D. Adeoye
Publication date: 19 October 2023
Published in: Computational Optimization and Applications (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2112.07344
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Lectures on convex optimization
- On the limited memory BFGS method for large scale optimization
- Sub-sampled Newton methods
- Minimizing uniformly convex functions by cubic regularization of Newton method
- Finite-sample analysis of \(M\)-estimators using self-concordance
- Generalized self-concordant functions: a recipe for Newton-type methods
- A branch and bound algorithm for the global optimization of Hessian Lipschitz continuous functions
- Cubic regularization of Newton method and its global performance
- On the structure of regularization paths for piecewise differentiable regularization terms
- Majorization-minimization-based Levenberg-Marquardt method for constrained nonlinear least squares
- On the Use of Stochastic Hessian Information in Optimization Methods for Machine Learning
- Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent
- Large-Scale Machine Learning with Stochastic Gradient Descent
- An Algorithm for Least-Squares Estimation of Nonlinear Parameters
- Updating Quasi-Newton Matrices with Limited Storage
- Generalized Linear Models With Examples in R
- Optimization Methods for Large-Scale Machine Learning
- Accuracy and Stability of Numerical Algorithms
- Multiple View Geometry in Computer Vision
- Understanding approximate Fisher information for fast convergence of natural gradient descent in wide neural networks*
- Reconciling modern machine-learning practice and the classical bias–variance trade-off
- A Stochastic Approximation Method
- Enlargement Methods for Computing the Inverse Matrix
- A method for the solution of certain non-linear problems in least squares
