Hybrid stochastic-deterministic minibatch proximal gradient: Less-than-single-pass optimization with nearly optimal generalization

Stochastic variance-reduced gradient (SVRG) algorithms have been shown to work favorably in solving large-scale learning problems. Despite the remarkable success, the stochastic gradient complexity of SVRG-type algorithms usually scales linearly with data size and thus could still be expensive for h...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHOU, Pan, YUAN, Xiaotong
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9030
https://ink.library.smu.edu.sg/context/sis_research/article/10033/viewcontent/2020_ICML_HSDN.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10033
record_format dspace
spelling sg-smu-ink.sis_research-100332024-07-25T08:01:39Z Hybrid stochastic-deterministic minibatch proximal gradient: Less-than-single-pass optimization with nearly optimal generalization ZHOU, Pan YUAN, Xiaotong Stochastic variance-reduced gradient (SVRG) algorithms have been shown to work favorably in solving large-scale learning problems. Despite the remarkable success, the stochastic gradient complexity of SVRG-type algorithms usually scales linearly with data size and thus could still be expensive for huge data. To address this deficiency, we propose a hybrid stochastic-deterministic minibatch proximal gradient (HSDMPG) algorithm for strongly-convex problems that enjoys provably improved data-size-independent complexity guarantees. 2020-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9030 https://ink.library.smu.edu.sg/context/sis_research/article/10033/viewcontent/2020_ICML_HSDN.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
spellingShingle Databases and Information Systems
ZHOU, Pan
YUAN, Xiaotong
Hybrid stochastic-deterministic minibatch proximal gradient: Less-than-single-pass optimization with nearly optimal generalization
description Stochastic variance-reduced gradient (SVRG) algorithms have been shown to work favorably in solving large-scale learning problems. Despite the remarkable success, the stochastic gradient complexity of SVRG-type algorithms usually scales linearly with data size and thus could still be expensive for huge data. To address this deficiency, we propose a hybrid stochastic-deterministic minibatch proximal gradient (HSDMPG) algorithm for strongly-convex problems that enjoys provably improved data-size-independent complexity guarantees.
format text
author ZHOU, Pan
YUAN, Xiaotong
author_facet ZHOU, Pan
YUAN, Xiaotong
author_sort ZHOU, Pan
title Hybrid stochastic-deterministic minibatch proximal gradient: Less-than-single-pass optimization with nearly optimal generalization
title_short Hybrid stochastic-deterministic minibatch proximal gradient: Less-than-single-pass optimization with nearly optimal generalization
title_full Hybrid stochastic-deterministic minibatch proximal gradient: Less-than-single-pass optimization with nearly optimal generalization
title_fullStr Hybrid stochastic-deterministic minibatch proximal gradient: Less-than-single-pass optimization with nearly optimal generalization
title_full_unstemmed Hybrid stochastic-deterministic minibatch proximal gradient: Less-than-single-pass optimization with nearly optimal generalization
title_sort hybrid stochastic-deterministic minibatch proximal gradient: less-than-single-pass optimization with nearly optimal generalization
publisher Institutional Knowledge at Singapore Management University
publishDate 2020
url https://ink.library.smu.edu.sg/sis_research/9030
https://ink.library.smu.edu.sg/context/sis_research/article/10033/viewcontent/2020_ICML_HSDN.pdf
_version_ 1814047712357646336