Second-order stochastic optimization for machine learning in linear time
From MaRDI portal
Recommendations
- Large-scale machine learning with stochastic gradient descent
- Stochastic sub-sampled Newton method with variance reduction
- Utilizing second order information in minibatch stochastic variance reduced proximal iterations
- On the use of stochastic Hessian information in optimization methods for machine learning
- Nesterov's acceleration for approximate Newton
Cites work
- A Family of Variable-Metric Methods Derived by Variational Means
- A new approach to variable metric algorithms
- A Stochastic Approximation Method
- A stochastic quasi-Newton method for large-scale optimization
- Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
- Adaptive subgradient methods for online learning and stochastic optimization
- An accelerated randomized proximal coordinate gradient method and its application to regularized empirical risk minimization
- Approximate Newton methods
- Conditioning of Quasi-Newton Methods for Function Minimization
- Exact and inexact subsampled Newton methods for optimization
- Finding approximate local minima faster than gradient descent
- scientific article; zbMATH DE number 3850830 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Introductory lectures on convex optimization. A basic course.
- Katyusha: the first direct acceleration of stochastic gradient methods
- Nearly tight oblivious subspace embeddings by trace inequalities
- On the use of stochastic Hessian information in optimization methods for machine learning
- Oracle complexity of second-order methods for smooth convex optimization
- Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
- Randomized Sketches of Convex Programs With Sharp Guarantees
- RES: Regularized Stochastic BFGS Algorithm
- Stochastic dual coordinate ascent methods for regularized loss minimization
- The Convergence of a Class of Double-rank Minimization Algorithms
- Uniform sampling for matrix approximation
- User-friendly tail bounds for sums of random matrices
Cited in
(43)- Sub-sampled Newton methods
- Periodic step-size adaptation in second-order gradient descent for single-pass on-line structured learning
- On the local convergence of a stochastic semismooth Newton method for nonsmooth nonconvex optimization
- A subsampling approach for Bayesian model selection
- Stronger data poisoning attacks break data sanitization defenses
- A stochastic extra-step quasi-Newton method for nonsmooth nonconvex optimization
- Combining stochastic adaptive cubic regularization with negative curvature for nonconvex optimization
- Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions
- Parallel optimization techniques for machine learning
- scientific article; zbMATH DE number 6982909 (Why is no real title available?)
- Utilizing second order information in minibatch stochastic variance reduced proximal iterations
- Optimization methods for large-scale machine learning
- Nesterov's acceleration for approximate Newton
- Approximate Newton methods
- Second-Order Online Nonconvex Optimization
- A fully stochastic second-order trust region method
- Sketched Newton-Raphson
- An investigation of Newton-sketch and subsampled Newton methods
- Stochastic proximal quasi-Newton methods for non-convex composite optimization
- Stochastic sub-sampled Newton method with variance reduction
- Regularization via mass transportation
- A stochastic semismooth Newton method for nonsmooth nonconvex optimization
- The common-directions method for regularized empirical risk minimization
- Automatic, dynamic, and nearly optimal learning rate specification via local quadratic approximation
- Revisiting the fragility of influence functions
- An overview of stochastic quasi-Newton methods for large-scale machine learning
- Hyperfast second-order local solvers for efficient statistically preconditioned distributed optimization
- Hessian averaging in stochastic Newton methods achieves superlinear convergence
- On pseudoinverse-free block maximum residual nonlinear Kaczmarz method for solving large-scale nonlinear system of equations
- Resource-adaptive Newton's method for distributed learning
- A selective review on statistical methods for massive data computation: distributed computing, subsampling, and minibatch techniques
- Adaptive pruning-based Newton's method for distributed learning
- Trust region-type method under inexact gradient and inexact Hessian with convergence analysis
- Stochastic online optimization for cyber-physical and robotic systems
- Training multi-layer over-parametrized neural network in subquadratic time
- Review of mathematical optimization in federated learning
- Variance-Reduced Stochastic Optimization for Efficient Inference of Hidden Markov Models
- Statistical inference of constrained stochastic optimization via sketched sequential quadratic programming
- Training (overparametrized) neural networks in near-linear time
- Generalized subsampled Newton method for large-scale linear inequalities with Tikhonov regularization
- Block-randomized stochastic methods for tensor ring decomposition
- Complexity reduction in online stochastic Newton methods with potential \(\mathcal{O}(Nd)\) total cost
- Stochastic gradient variational Bayes in the stochastic blockmodel
This page was built for publication: Second-order stochastic optimization for machine learning in linear time
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4637040)
