The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems

In this work we investigate the practicability of stochastic gradient descent and recently introduced variants with variance-reduction techniques in imaging inverse problems, such as space-varying image deblurring. Such algorithms have been shown in machine learning literature to have optimal comple...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 7680 - 7684
Hlavní autori: Tang, Junqi, Egiazarian, Karen, Davies, Mike
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.05.2019
Predmet:
ISSN:2379-190X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In this work we investigate the practicability of stochastic gradient descent and recently introduced variants with variance-reduction techniques in imaging inverse problems, such as space-varying image deblurring. Such algorithms have been shown in machine learning literature to have optimal complexities in theory, and provide great improvement empirically over the full gradient methods. Surprisingly, in some tasks such as image deblurring, many of such methods fail to converge faster than the accelerated full gradient method (FISTA), even in terms of epoch counts. We investigate this phenomenon and propose a theory-inspired mechanism to characterize whether a given inverse problem should be preferred to be solved by stochastic optimization technique with a known sampling pattern. Furthermore, to overcome another key bottleneck of stochastic optimization which is the heavy computation of proximal operators while maintaining fast convergence, we propose an accelerated primal-dual SGD algorithm and demonstrate the effectiveness of our approach in image deblurring experiments.
AbstractList In this work we investigate the practicability of stochastic gradient descent and recently introduced variants with variance-reduction techniques in imaging inverse problems, such as space-varying image deblurring. Such algorithms have been shown in machine learning literature to have optimal complexities in theory, and provide great improvement empirically over the full gradient methods. Surprisingly, in some tasks such as image deblurring, many of such methods fail to converge faster than the accelerated full gradient method (FISTA), even in terms of epoch counts. We investigate this phenomenon and propose a theory-inspired mechanism to characterize whether a given inverse problem should be preferred to be solved by stochastic optimization technique with a known sampling pattern. Furthermore, to overcome another key bottleneck of stochastic optimization which is the heavy computation of proximal operators while maintaining fast convergence, we propose an accelerated primal-dual SGD algorithm and demonstrate the effectiveness of our approach in image deblurring experiments.
Author Egiazarian, Karen
Tang, Junqi
Davies, Mike
Author_xml – sequence: 1
  givenname: Junqi
  surname: Tang
  fullname: Tang, Junqi
  organization: School of Engineering, University of Edinburgh, UK
– sequence: 2
  givenname: Karen
  surname: Egiazarian
  fullname: Egiazarian, Karen
  organization: Noiseless Imaging Ltd, Finland
– sequence: 3
  givenname: Mike
  surname: Davies
  fullname: Davies, Mike
  organization: School of Engineering, University of Edinburgh, UK
BookMark eNotkNFqwjAYRrOxwdT5BN7kBer-JK1JLkU2FQoTdLA7SdK_M6NNRxIGe_sV9OpcHDh8fFPyEIaAhCwYLBkD_bLfrI_Hw5ID00u1UkKs1B2Za6lYKbVWTDB2TyZcSF0wDZ9PZJrSNwAoWaoJOZ8uSGvf-2yyHwI1oaGHaFz2znR07Rx2GK9qaOkxD-5i0ijpNprGY8h03X0N0edLn6gPdB9-MSYcG4PtsE_P5LE1XcL5jTPy8fZ62uyK-n07Lq8LzznkAtWIqrLSgmg1WHCl0FqXlktsGa-kggZXaJvKCQnOgdXGGmQcoILSODEji2vXI-L5J_rexL_z7Q_xD-61V2U
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICASSP.2019.8683368
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9781479981311
1479981311
EISSN 2379-190X
EndPage 7684
ExternalDocumentID 8683368
Genre orig-research
GroupedDBID 23M
29P
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i220t-e822055b7b03f90b0c439994b27ef125780de6ebd5c370cc0b9abae1200504ac3
IEDL.DBID RIE
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000482554007182&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:33:28 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i220t-e822055b7b03f90b0c439994b27ef125780de6ebd5c370cc0b9abae1200504ac3
OpenAccessLink https://www.pure.ed.ac.uk/ws/files/206650698/icassp2019.pdf
PageCount 5
ParticipantIDs ieee_primary_8683368
PublicationCentury 2000
PublicationDate 2019-May
PublicationDateYYYYMMDD 2019-05-01
PublicationDate_xml – month: 05
  year: 2019
  text: 2019-May
PublicationDecade 2010
PublicationTitle Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998)
PublicationTitleAbbrev ICASSP
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0008748
Score 2.1535468
Snippet In this work we investigate the practicability of stochastic gradient descent and recently introduced variants with variance-reduction techniques in imaging...
SourceID ieee
SourceType Publisher
StartPage 7680
SubjectTerms Acceleration
Convergence
Gradient methods
Image Processing
Inverse problems
Machine learning
Stochastic Optimization
Task analysis
Title The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems
URI https://ieeexplore.ieee.org/document/8683368
WOSCitedRecordID wos000482554007182&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7a4kEvPlrxTQ4eXZt9dJMcS_F1KYUq9FbymLULuiu7W3-_SbZUBS_eQiAMzCT5yGS-bwCuVZgJk6Q0cH9UQcKNsPegDAOmUY0kUpfp980m2HTKFwsx68DNlguDiL74DG_d0P_lm1KvXapsyFMexynvQpextOVqbW9dzhK-URUKqRg-Tcbz-cyVbtm90C771T_Fw8f9_v8MH8Dgm4dHZluEOYQOFkew90NCsA9LG2fiWUrexUQWhrQaRNb5ZKy1hZU2yKTMyLwp9Uo6aWbyUPlir4aM317LKm9W7zXJC-J0N6ram3WNZuoBvNzfPU8eg03ThCCPItoEyB11dqSYonEmqKLavThEoiKGWegOKDWYojIjHTOqNVVCKomhyy7RROr4GHpFWeAJEKlSo5EKpZgFcowFZlmWaEYxiaSFt1PoO1ctP1pdjOXGS2d_T5_DrotGWyx4Ab2mWuMl7OjPJq-rKx_ML5IGoiw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8NAEB1qFdSLH6347R48Grv5aDZ7LMXaYi2FVugt7G4mtqCJJKm_3-wmVAUv3kIgDMxk97Gz894DuJV2zCPPp5a-o7K8IOLlPihsiymUXYFUd_qN2QSbTILFgk8bcLfhwiCiGT7De_1o7vKjVK11q6wT-IHr-sEWbGvnrJqttdl3A-YFta6QTXln1O_NZlM9vFX-DdWHvxxUDIAMDv4X-hDa30w8Mt1gzBE0MDmG_R8igi0Iy0oTw1MySSYiiUilQlSmn_SUKoGlKjNJYzIrUrUUWpyZPGZm3KsgvbfXNFsVy_ecrBKilTey3ITVVjN5G14GD_P-0KptE6yV49DCwkCTZ7uSSerGnEqq9JmDe9JhGNt6idIIfZRRV7mMKkUlF1KgrftL1BPKPYFmkiZ4CkRIP1JIuZSshHJ0OcZx7ClG0XNECXBn0NKpCj8qZYywztL5369vYHc4fx6H49Hk6QL2dGWq0cFLaBbZGq9gR30Wqzy7NoX9AjEzpXU
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+of+the+...+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%281998%29&rft.atitle=The+Limitation+and+Practical+Acceleration+of+Stochastic+Gradient+Algorithms+in+Inverse+Problems&rft.au=Tang%2C+Junqi&rft.au=Egiazarian%2C+Karen&rft.au=Davies%2C+Mike&rft.date=2019-05-01&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=7680&rft.epage=7684&rft_id=info:doi/10.1109%2FICASSP.2019.8683368&rft.externalDocID=8683368