Shankar Krishnan
6 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (6)
π
Cross-Pollinator
(12)
πΊοΈ
Taxonomy Completionist
(16)
π
Conference Pioneer
Conferences
ICLR (2)
ICML (2)
CVPR (1)
NIPS (1)
Top co-authors
Keywords
neural network optimization
(2)
batch normalization
(2)
language model
(2)
few-shot learning
(1)
transfer learning
(1)
natural language processing
(1)
model pretraining
(1)
deep learning
(1)
gradient descent
(1)
deep neural network
(1)
inductive bia
(1)
hessian eigenvalue
(1)
model training
(1)
normalization layer
(1)
reasoning ability
(1)
gradual stacking
(1)
eigenvalue spectrum
(1)
progressive stacking
(1)
filter response normalization
(1)
mini-batch statistics
(1)
Papers
On the Inductive Bias of Stacking Towards Improving Reasoning
NIPS 2024
Efficient Training of Language Models using Few-Shot Learning
ICML 2023
A unifying view on implicit bias in training linear neural networks
ICLR 2021
Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks
CVPR 2020
An Investigation into Neural Net Optimization via Hessian Eigenvalue Density
ICML 2019
Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
ICLR 2018