Login / Signup
Erin George
ORCID
Publication Activity (10 Years)
Years Active: 2021-2024
Publications (10 Years): 7
Top Topics
Regression Algorithm
Hinge Loss
Noisy Data
Dynamical Systems
Top Venues
CoRR
SIAM J. Appl. Dyn. Syst.
IEEECONF
NeurIPS
</>
Publications
</>
Kedar Karhadkar
,
Erin George
,
Michael Murray
,
Guido Montúfar
,
Deanna Needell
Benign overfitting in leaky ReLU networks with moderate input dimension.
CoRR
(2024)
Erin George
,
Joyce Chew
,
Deanna Needell
Detecting and Mitigating Indirect Stereotypes in Word Embeddings.
CoRR
(2023)
Erin George
,
Michael Murray
,
William Swartworth
,
Deanna Needell
Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?
NeurIPS
(2023)
Erin George
,
Michael Murray
,
William Swartworth
,
Deanna Needell
Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?
CoRR
(2023)
Erin George
,
Yotam Yaniv
,
Deanna Needell
Multi-Randomized Kaczmarz for Latent Class Regression.
IEEECONF
(2022)
Erin George
,
Yotam Yaniv
,
Deanna Needell
Multi-Randomized Kaczmarz for Latent Class Regression.
CoRR
(2022)
Erin George
,
Colleen E. Chan
,
Gal Dimand
,
Ryan M. Chakmak
,
Claudia Falcon
,
Daniel Eckhardt
,
Robert Scott Martin
Decomposing Signals from Dynamical Systems Using Shadow Manifold Interpolation.
SIAM J. Appl. Dyn. Syst.
20 (4) (2021)