SketchySGD: reliable stochastic optimization via randomized curvature estimates

[[Person:6166050|Author name not available (Why is that?)]], Shipu Zhao, Madeleine Udell, Pratik Rathore

Publication date: 16 January 2025

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

zbMATH Keywords

stochastic optimization preconditioning Nyström approximation stochastic gradient descent randomized low-rank approximation

Mathematics Subject Classification ID

Convex programming (90C25) Stochastic programming (90C15) Methods of quasi-Newton type (90C53)

Cites Work

Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
Lectures on convex optimization
Fast global convergence of gradient methods for high-dimensional statistical recovery
On the limited memory BFGS method for large scale optimization
Sub-sampled Newton methods
Newton-type methods for non-convex optimization under inexact Hessian information
First-order and stochastic optimization methods for machine learning
Oracle complexity of second-order methods for smooth convex optimization
LSRN: A Parallel Iterative Solver for Strongly Over- or Underdetermined Systems
Convergence of Trust-Region Methods Based on Probabilistic Models
Computational Advertising: Techniques for Targeting Relevant Ads
Dimensionality Reduction for k-Means Clustering and Low Rank Approximation
Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence
On the Use of Stochastic Hessian Information in Optimization Methods for Machine Learning
Blendenpik: Supercharging LAPACK's Least-Squares Solver
Low-Rank Approximation and Regression in Input Sparsity Time
Robust Stochastic Approximation Approach to Stochastic Programming
An Algorithm for Least-Squares Estimation of Nonlinear Parameters
Estimating the Largest Eigenvalue by the Power and Lanczos Algorithms with a Random Start
Numerical Optimization
Practical Sketching Algorithms for Low-Rank Matrix Approximation
Accuracy and Stability of Numerical Algorithms
The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
Sketched Newton--Raphson
A Stochastic Line Search Method with Expected Complexity Analysis
Sparsity and incoherence in compressive sampling
A Stochastic Approximation Method
A method for the solution of certain non-linear problems in least squares
Exact and inexact subsampled Newton methods for optimization
Randomized numerical linear algebra: Foundations and algorithms
Newton-MR: inexact Newton method with minimum residual sub-problem solver
Randomized Nyström Preconditioning

This page was built for publication: SketchySGD: reliable stochastic optimization via randomized curvature estimates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6664471)