Author of the publication

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy.

E. Moroshko, B. Woodworth, S. Gunasekar, J. Lee, N. Srebro, and D. Soudry. NeurIPS, (2020)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

Edward Dotzel

Edward Hartstein

Edward Birkenbeil

Edward Haub

Edward Gough

Other publications of authors with the same name

Finite Sample Analysis Of Dynamic Regression Parameter Learning.M. Kozdoba, E. Moroshko, S. Mannor, and Y. Crammer. NeurIPS, (2022)Continual Learning in Linear Classification on Separable Data.I. Evron, E. Moroshko, G. Buzaglo, M. Khriesh, B. Marjieh, N. Srebro, and D. Soudry. ICML, volume 202 of Proceedings of Machine Learning Research, page 9440-9484. PMLR, (2023)Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy.E. Moroshko, B. Woodworth, S. Gunasekar, J. Lee, N. Srebro, and D. Soudry. NeurIPS, (2020)Weighted last-step min-max algorithm with improved sub-logarithmic regret.E. Moroshko, and K. Crammer. Theor. Comput. Sci., (2014)On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent.S. Azulay, E. Moroshko, M. Nacson, B. Woodworth, N. Srebro, A. Globerson, and D. Soudry. ICML, volume 139 of Proceedings of Machine Learning Research, page 468-477. PMLR, (2021)A Last-Step Regression Algorithm for Non-Stationary Online Learning.E. Moroshko, and K. Crammer. AISTATS, volume 31 of JMLR Workshop and Conference Proceedings, page 451-462. JMLR.org, (2013)Selective Sampling with Drift.E. Moroshko, and K. Crammer. AISTATS, volume 33 of JMLR Workshop and Conference Proceedings, page 651-659. JMLR.org, (2014)Efficient Loss-Based Decoding on Graphs for Extreme Classification.I. Evron, E. Moroshko, and K. Crammer. NeurIPS, page 7233-7244. (2018)Weighted Last-Step Min-Max Algorithm with Improved Sub-logarithmic Regret.E. Moroshko, and K. Crammer. ALT, volume 7568 of Lecture Notes in Computer Science, page 245-259. Springer, (2012)Online Regression with Controlled Label Noise Rate.E. Moroshko, and K. Crammer. ECML/PKDD (2), volume 10535 of Lecture Notes in Computer Science, page 355-369. Springer, (2017)

BibSonomy

Disambiguation of "Moroshko, Edward"

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy.

Please choose a person to relate this publication to

Edward Dotzel

Edward Hartstein

Edward Birkenbeil

Edward Haub

Edward Gough

Other publications of authors with the same name

Disambiguation

BibSonomy

Disambiguation of "Moroshko, Edward"

copydeleteadd this publication to your clipboardcommunity posthistory of this postURLDOIBibTeXEndNoteAPAChicagoDIN 1505HarvardMSOffice XML Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy.

Please choose a person to relate this publication to

Edward Dotzel

Edward Hartstein

Edward Birkenbeil

Edward Haub

Edward Gough

Other publications of authors with the same name

Disambiguation

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy.