Elad Hoffer
12 papers · 2017–2023 · 4 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 ↓+6 more ↓ Show less ↑
π£ Hot Topic Early Bird π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze πΊοΈ Taxonomy Completionist (23) π€ Dynamic Duo (12)
π§
Keyword Pioneer
π€
Dynamic Duo
(12)
β‘
Prolific Year Β· Productive
β
The Questioner
π
Century Club Β· Bronze
π
Conference Pioneer
Venues
Top co-authors
Research topics
Deep Learning
(12)
Machine Learning
(9)
Optimization & Theory Β· Deep Learning
(7)
Optimization & Theory Β· Machine Learning
(7)
Techniques
(7)
Application Areas
(4)
Learning Types Β· Deep Learning
(3)
Artificial Intelligence
(2)
Core AI
(2)
Architectures
(1)
Core Methods
(1)
Learning Types Β· Machine Learning
(1)
Keywords
batch normalization
(4)
stochastic gradient descent
(3)
gradient quantization
(3)
gradient descent
(2)
implicit regularization
(2)
model compression
(2)
neural network
(2)
separable data
(2)
logistic regression
(2)
large batch training
(2)
neural network training
(2)
learning rate
(1)
distributed training
(1)
convergence rate
(1)
knowledge distillation
(1)
synthetic data generation
(1)
generalization gap
(1)
efficient inference
(1)
weight decay
(1)
asynchronous training
(1)
Papers
Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
ICLR 2023
DropCompute: simple and more robust distributed synchronous training via compute variance reduction
NeurIPS 2023
Neural gradients are near-lognormal: improved quantized and sparse training
ICLR 2021
At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?
ICLR 2020
Augment Your Batch: Improving Generalization Through Instance Repetition
CVPR 2020
The Knowledge Within: Methods for Data-Free Model Compression
CVPR 2020
Fix your classifier: the marginal value of training the last weight layer
ICLR 2018
Norm matters: efficient and accurate normalization schemes in deep networks
NeurIPS 2018
Scalable methods for 8-bit training of neural networks
NeurIPS 2018
The Implicit Bias of Gradient Descent on Separable Data
ICLR 2018
The Implicit Bias of Gradient Descent on Separable Data
JMLR 2018
Train longer, generalize better: closing the generalization gap in large batch training of neural networks
NeurIPS 2017