OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
George E. Dahl
Research Scientist, Google
Joined
September 2016
Names
George E. Dahl
(Preferred)
,
George Edward Dahl
,
George Dahl
Emails
****@google.com
(Confirmed)
,
****@gmail.com
(Confirmed)
,
****@cs.toronto.edu
(Confirmed)
Personal Links
Homepage
Google Scholar
DBLP
Career & Education History
Research Scientist
Google
(google.com)
2015
–
Present
PhD student
Department of Computer Science, University of Toronto
(cs.toronto.edu)
2008
–
2015
Advisors, Relations & Conflicts
No relations added
Expertise
deep learning
,
nlp
,
speech
,
natural language processing
Present
Publications
How far away are truly hyperparameter-free learning algorithms?
Priya Kasimbeg
,
Vincent Roulet
,
Naman Agarwal
,
Sourabh Medapati
,
Fabian Pedregosa
,
Atish Agarwala
,
George E. Dahl
Accepted by TMLR
Readers:
Everyone
Pre-trained Gaussian Processes for Bayesian Optimization
Zi Wang
,
George E. Dahl
,
Kevin Swersky
,
Chansoo Lee
,
Zachary Nado
,
Justin Gilmer
,
Jasper Snoek
,
Zoubin Ghahramani
Journal of Machine Learning Research
Readers:
Everyone
Accelerating neural network training: An analysis of the AlgoPerf competition
Priya Kasimbeg
,
Frank Schneider
,
Runa Eschenhagen
,
Juhan Bae
,
Chandramouli Shama Sastry
,
Mark Saroufim
,
BOYUAN FENG
,
Less Wright
,
Edward Z. Yang
,
Zachary Nado
,
Sourabh Medapati
,
Philipp Hennig
,
Michael Rabbat
,
George E. Dahl
ICLR 2025 Poster
Readers:
Everyone
Adaptive Gradient Methods at the Edge of Stability
Jeremy Cohen
,
Behrooz Ghorbani
,
Shankar Krishnan
,
Naman Agarwal
,
Sourabh Medapati
,
Michal Badura
,
Daniel Suo
,
Zachary Nado
,
George E. Dahl
,
Justin Gilmer
HeavyTails 2023
Readers:
Everyone
A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes
Zachary Nado
,
Justin Gilmer
,
Christopher J Shallue
,
Rohan Anil
,
George Edward Dahl
Published: 28 Jan 2022, Last Modified: 12 Oct 2025
ICLR 2022 Submitted
Readers:
Everyone
A Loss Curvature Perspective on Training Instabilities of Deep Learning Models
Justin Gilmer
,
Behrooz Ghorbani
,
Ankush Garg
,
Sneha Kudugunta
,
Behnam Neyshabur
,
David Cardoze
,
George Edward Dahl
,
Zachary Nado
,
Orhan Firat
Published: 28 Jan 2022, Last Modified: 12 Oct 2025
ICLR 2022 Poster
Readers:
Everyone
Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers
Zi Wang
,
George Edward Dahl
,
Kevin Swersky
,
Chansoo Lee
,
Zelda E Mariet
,
Zachary Nado
,
Justin Gilmer
,
Jasper Snoek
,
Zoubin Ghahramani
Published: 28 Jan 2022, Last Modified: 12 Oct 2025
ICLR 2022 Submitted
Readers:
Everyone
A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes
Zachary Nado
,
Justin Gilmer
,
Christopher J Shallue
,
Rohan Anil
,
George Edward Dahl
21 May 2021 (modified: 26 May 2025)
NeurIPS 2021 Submitted
Readers:
Everyone
A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes
Zachary Nado
,
Justin Gilmer
,
Christopher J. Shallue
,
Rohan Anil
,
George E. Dahl
2021 (modified: 03 Nov 2022)
CoRR 2021
Readers:
Everyone
What Will it Take to Fix Benchmarking in Natural Language Understanding?
Samuel R. Bowman
,
George E. Dahl
2021 (modified: 09 Sept 2021)
NAACL-HLT 2021
Readers:
Everyone
View all 48 publications
Co-Authors
Abdel-rahman Mohamed
Adam Santoro
Aleksandr Y. Aravkin
Aleksei Timofeev
Aleksey Boyko
Alex Acero
Alexandre Passos
Alvaro Sanchez-Gonzalez
Andrea Tacchetti
Andrew J. Ballard
Andrew M. Dai
Andy Liaw
Ankush Garg
Ashish Vaswani
Atish Agarwala
BOYUAN FENG
Behnam Neyshabur
Behrooz Ghorbani
Bhuvana Ramabhadran
Bhuwan Dhingra
Brian Kingsbury
Chandramouli Shama Sastry
Chansoo Lee
Charles Nash
Chris Dyer
View all 126 co-authors