2015
DOI: 10.1007/s10107-015-0864-7
|View full text |Cite
|
Sign up to set email alerts
|

Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm

Abstract: ABSTRACT. We obtain an improved finite-sample guarantee on the linear convergence of stochastic gradient descent for smooth and strongly convex objectives, improving from a quadratic dependence on the conditioning (L/µ) 2 (where L is a bound on the smoothness and µ on the strong convexity) to a linear dependence on L/µ. Furthermore, we show how reweighting the sampling distribution (i.e. importance sampling) is necessary in order to further improve convergence, and obtain a linear dependence in the average smo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

5
403
1
2

Year Published

2016
2016
2023
2023

Publication Types

Select...
8

Relationship

2
6

Authors

Journals

citations
Cited by 354 publications
(418 citation statements)
references
References 41 publications
5
403
1
2
Order By: Relevance
“…The relation of these approaches to coordinate descent and gradient descent methods has also been recently studied, see e.g. [GO12,Dum14,NSW14a [LW15,LMY15], and the use of preconditioning [GPS16]. Some other references on recent work include [CP12,RM12] For the most part, it seems that these two branches of research which address the same problems have been developing disjointly from each other.…”
Section: Introductionmentioning
confidence: 99%
“…The relation of these approaches to coordinate descent and gradient descent methods has also been recently studied, see e.g. [GO12,Dum14,NSW14a [LW15,LMY15], and the use of preconditioning [GPS16]. Some other references on recent work include [CP12,RM12] For the most part, it seems that these two branches of research which address the same problems have been developing disjointly from each other.…”
Section: Introductionmentioning
confidence: 99%
“…Recently, these methods have received significant attention due to their simplicity and effectiveness (see, e.g., [7]- [13]). In particular, Nemirovski et.…”
Section: Introductionmentioning
confidence: 99%
“…We believe it shall have lots of more other interesting applications including theoretical and numerical aspects. In fact, it was observed in the most recent paper [8], where stochastic gradient descent and randomized Kaczmarz algorithm were studied, that the strong convexity assumption can be replaced by the restricted strong convexity without destroying the convergence behavior. 3 …”
Section: Discussionmentioning
confidence: 95%
“…4.2, then all the results in [13] for IGM applying to (32) automatically hold and can even be strengthened. Thirdly, due to the similarity between inequalities (3) and (2), the RSC property can be directly replace the strong convexity for convergence analysis of stochastic gradient methods [8] while the global error bound condition might not. 2 …”
Section: Algorithm 4 Inexact Gradient Descent Methodsmentioning
confidence: 99%
See 1 more Smart Citation