On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control

Thuan Nguyen; Matthias Scheutz; Shuchin Aeron

doi:10.1109/MLSP55844.2023.10286000

On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control

Thuan Nguyen
, Matthias Scheutz
, Shuchin Aeron

Department of Engineering, Engineering Technology, Interior Architecture, and Surveying

Tufts University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Original language	English
Title of host publication	Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023
Editors	Danilo Comminiello, Michele Scarpiniti
Publisher	IEEE Computer Society
ISBN (Electronic)	9798350324112
DOIs	https://doi.org/10.1109/MLSP55844.2023.10286000
State	Published - 2023
Event	33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023 - Rome, Italy Duration: Sep 17 2023 → Sep 20 2023

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume	2023-September
ISSN (Print)	2161-0363
ISSN (Electronic)	2161-0371

Conference

Conference	33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023
Country/Territory	Italy
City	Rome
Period	9/17/23 → 9/20/23

ASJC Scopus Subject Areas

Human-Computer Interaction
Signal Processing

Keywords

classification error constraints
Domain generalization
multiple domain-invariant features

Access to Document

10.1109/MLSP55844.2023.10286000

Cite this

Nguyen, T., Scheutz, M., & Aeron, S. (2023). On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control. In D. Comminiello, & M. Scarpiniti (Eds.), Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2023-September). IEEE Computer Society. https://doi.org/10.1109/MLSP55844.2023.10286000

On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control. / Nguyen, Thuan; Scheutz, Matthias; Aeron, Shuchin.
Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023. ed. / Danilo Comminiello; Michele Scarpiniti. IEEE Computer Society, 2023. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2023-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Nguyen, T, Scheutz, M & Aeron, S 2023, On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control. in D Comminiello & M Scarpiniti (eds), Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023. IEEE International Workshop on Machine Learning for Signal Processing, MLSP, vol. 2023-September, IEEE Computer Society, 33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023, Rome, Italy, 9/17/23. https://doi.org/10.1109/MLSP55844.2023.10286000

Nguyen T, Scheutz M, Aeron S. On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control. In Comminiello D, Scarpiniti M, editors, Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023. IEEE Computer Society. 2023. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). doi: 10.1109/MLSP55844.2023.10286000

Nguyen, Thuan ; Scheutz, Matthias ; Aeron, Shuchin. / On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control. Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023. editor / Danilo Comminiello ; Michele Scarpiniti. IEEE Computer Society, 2023. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).

@inproceedings{2a3e94f629af4c37bbd6fb1d1faafb83,

title = "On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control",

keywords = "classification error constraints, Domain generalization, multiple domain-invariant features",

author = "Thuan Nguyen and Matthias Scheutz and Shuchin Aeron",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023 ; Conference date: 17-09-2023 Through 20-09-2023",

year = "2023",

doi = "10.1109/MLSP55844.2023.10286000",

language = "English",

series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

publisher = "IEEE Computer Society",

editor = "Danilo Comminiello and Michele Scarpiniti",

booktitle = "Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023",

}

TY - GEN

T1 - On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control

AU - Nguyen, Thuan

AU - Scheutz, Matthias

AU - Aeron, Shuchin

PY - 2023

Y1 - 2023

KW - classification error constraints

KW - Domain generalization

KW - multiple domain-invariant features

UR - https://www.scopus.com/pages/publications/85177195927

UR - https://www.scopus.com/pages/publications/85177195927#tab=citedBy

U2 - 10.1109/MLSP55844.2023.10286000

DO - 10.1109/MLSP55844.2023.10286000

M3 - Conference contribution

AN - SCOPUS:85177195927

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023

A2 - Comminiello, Danilo

A2 - Scarpiniti, Michele

PB - IEEE Computer Society

T2 - 33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023

Y2 - 17 September 2023 through 20 September 2023

ER -

On The Failure of Invariant Risk Minimization and an Effective fix via Classification Error Control

Publication series

Conference

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Cite this