Yamini Bansal
6 papers · 2018–2023 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (10) π£ Hot Topic Early Bird
π
Conference Pioneer
Venues
Top co-authors
Research topics
Keywords
neural machine translation
(2)
stochastic gradient descent
(2)
self-supervised learning
(2)
representation learning
(2)
information bottleneck
(1)
machine translation
(1)
in-context learning
(1)
prompt-based learning
(1)
neural representation
(1)
low-resource language
(1)
deep neural network
(1)
generalization gap
(1)
test performance
(1)
model size
(1)
centered kernel alignment
(1)
data scaling
(1)
model stitching
(1)
training epoch
(1)
power law
(1)
scaling exponent
(1)
Papers
The Unreasonable Effectiveness of Few-shot Learning for Machine Translation
ICML 2023
Data Scaling Laws in NMT: The Effect of Noise and Architecture
ICML 2022
For self-supervised learning, Rationality implies generalization, provably
ICLR 2021
Revisiting Model Stitching to Compare Neural Representations
NeurIPS 2021
Deep Double Descent: Where Bigger Models and More Data Hurt
ICLR 2020
On the Information Bottleneck Theory of Deep Learning
ICLR 2018