Yann N. Dauphin
8 papers · 2011–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (16) π Interdisciplinary Bridge π Academic Marathon (13) π Cross-Pollinator (13) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(3)
π
Trend Setter
π
Conference Pioneer
Conferences
NIPS (4)
ICLR (2)
ICML (2)
Top co-authors
Keywords
neural network training
(2)
convolutional neural network
(2)
gradient descent
(2)
manifold learning
(1)
attention mechanism
(1)
machine translation
(1)
batch normalization
(1)
text generation
(1)
language modeling
(1)
deep learning
(1)
singular value decomposition
(1)
semi-supervised classification
(1)
optimization theory
(1)
contractive autoencoders
(1)
semi-supervised hypothesis
(1)
autoencoders
(1)
second-order optimization
(1)
weight initialization
(1)
saddle point
(1)
newton method
(1)
Papers
Neglected Hessian component explains mysteries in sharpness regularization
NIPS 2024
Fixup Initialization: Residual Learning Without Normalization
ICLR 2019
MetaInit: Initializing learning by learning to initialize
NIPS 2019
mixup: Beyond Empirical Risk Minimization
ICLR 2018
Convolutional Sequence to Sequence Learning
ICML 2017
Language Modeling with Gated Convolutional Networks
ICML 2017
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
NIPS 2014
The Manifold Tangent Classifier
NIPS 2011