Subsampled first-order optimization methods with applications in imaging

DOI10.1007/978-3-030-98661-2_78zbMATH Open1548.90392MaRDI QIDQ6606441FDOQ6606441

Authors: Stefania Bellavia, Tommaso Bianconcini, Nataša Krejić, Benedetta Morini

Publication date: 16 September 2024

first-order methods stochastic gradient neural networks convolutional neural networks image classification finite-sum minimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of mathematical programming (90C90) Nonconvex programming, global optimization (90C26) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10)

Cites Work

The elements of statistical learning. Data mining, inference, and prediction
Numerical Optimization
Pattern recognition and machine learning.
A stochastic quasi-Newton method for large-scale optimization
Learning representations by back-propagating errors
A Stochastic Approximation Method
The Barzilai and Borwein Gradient Method for the Large Scale Unconstrained Minimization Problem
Two-Point Step Size Gradient Methods
Title not available (Why is that?)
Robust Stochastic Approximation Approach to Stochastic Programming
On stochastic gradient and subgradient methods with adaptive steplength sequences
Sample size selection in optimization methods for machine learning
Introduction to Stochastic Search and Optimization
An Introduction to Matrix Concentration Inequalities
Minimization of functions having Lipschitz continuous first partial derivatives
Gradient Convergence in Gradient methods with Errors
On the behavior of the gradient norm in the steepest descent method
Nonlinear stepsize control, trust regions and regularizations for unconstrained optimization
Stochastic Estimation of the Maximum of a Regression Function
Stochastic optimization using a trust-region method and random models
Title not available (Why is that?)
A Scaled Stochastic Approximation Algorithm
New stochastic approximation algorithms with adaptive step sizes
Nonmonotone line search methods with variable sample size
A gradient method for unconstrained optimization in noisy environment
Hybrid deterministic-stochastic methods for data fitting
Accelerated Stochastic Approximation
Accelerated Stochastic Approximation
Minimizing finite sums with the stochastic average gradient
A Stochastic Line Search Method with Expected Complexity Analysis
Efficient sample sizes in stochastic nonlinear programming
Line search methods with variable sample size for unconstrained optimization
Inexact restoration approach for minimization with inexact evaluation of the objective function
Descent direction method with line search for unconstrained optimization in noisy environment
Optimization Methods for Large-Scale Machine Learning
Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
Sub-sampled Newton methods
Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence
An investigation of Newton-Sketch and subsampled Newton methods
Exact and inexact subsampled Newton methods for optimization
Newton-type methods for non-convex optimization under inexact Hessian information
Adaptive cubic regularization methods with dynamic inexact Hessian information and applications to finite-sum minimization
Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization
Subsampled inexact Newton methods for minimizing large sums of convex functions
Neural Networks and Deep Learning
Title not available (Why is that?)
Inexact restoration with subsampled trust-region methods for finite-sum minimization
On the employment of inexact restoration for the minimization of functions whose evaluation is subject to errors

This page was built for publication: Subsampled first-order optimization methods with applications in imaging

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6606441)