Sample size selection in optimization methods for machine learning

Keywords

Hessian matrixMathematicsMathematical optimizationSubspace topologyGradient methodAlgorithmSample size determinationComputationFunction (biology)Projection (relational algebra)Sample (material)Gradient descentApplied mathematicsComputer scienceArtificial intelligenceStatisticsMathematical analysis

Affiliated Institutions

Related Publications

Pegasos

Shai Shalev‐Shwartz , Yoram Singer , Nathan Srebro

We describe and analyze a simple and effective iterative algorithm for solving the optimization problem cast by Support Vector Machines (SVM). Our method alternates between stoc...

2007 980 citations

Efficient projections onto the<i>l</i><sub>1</sub>-ball for learning in high dimensions

John C. Duchi , Shai Shalev‐Shwartz , Yoram Singer +1 more

We describe efficient algorithms for projecting a vector onto the ℓ1-ball. We present two methods for projection. The first performs exact projection in O(n) expected time, wher...

2008 1202 citations

Conjugate Gradient Methods with Inexact Searches

David F. Shanno

Conjugate gradient methods are iterative methods for finding the minimizer of a scalar function f(x) of a vector variable x which do not update an approximation to the inverse H...

1978 Mathematics of Operations Research 470 citations

On the Global Convergence of a Filter--SQP Algorithm

R. Fletcher , Sven Leyffer , Philippe L. Toint

A mechanism for proving global convergence in SQP-filter methods for nonlinear programming (NLP) is described. Such methods are characterized by their use of the dominance conce...

2002 SIAM Journal on Optimization 319 citations

Large-Scale Machine Learning with Stochastic Gradient Descent

Léon Bottou

During the last decade, the data sizes have grown faster than the speed of processors. In this context, the capabilities of statistical machine learning methods is limited by th...

2010 5479 citations

Publication Info

Year: 2012
Type: article
Volume: 134
Issue: 1
Pages: 127-155
Citations: 379
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Sample size selection in optimization methods for machine learning

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

379

OpenAlex

Cite This

APA Style

                            
                                
                                    Richard H. Byrd, 
                                
                                    Gillian M. Chin, 
                                
                                    Jorge Nocedal
                                
                                et al.
                            
                            (2012). 
                            Sample size selection in optimization methods for machine learning. 
                            Mathematical Programming
                            , 134
                            (1)
                            , 127-155.
                            https://doi.org/10.1007/s10107-012-0572-5
                        

Identifiers

DOI: 10.1007/s10107-012-0572-5