Elad Hoffer
12 papers · 2017–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🏃 Academic Marathon (6) 🌍 Conference Polyglot (4) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (10)
🐝
Cross-Pollinator
(10)
🌉
Interdisciplinary Bridge
🤝
Dynamic Duo
(12)
❓
The Questioner
⚡
Prolific Year
(5)
🚀
Conference Pioneer
📈
Trend Setter
💎
Century Club
(12)
Conferences
ICLR (5)
NIPS (4)
CVPR (2)
JMLR (1)
Top co-authors
Keywords
batch normalization
(4)
stochastic gradient descent
(2)
model compression
(2)
knowledge distillation
(1)
data-free learning
(1)
efficient inference
(1)
synthetic data generation
(1)
gradient descent
(1)
convergence rate
(1)
implicit regularization
(1)
weight decay
(1)
generalization gap
(1)
numerical stability
(1)
gradient variance
(1)
separable datum
(1)
weight normalization
(1)
deep network
(1)
gradient quantization
(1)
synthetic sample
(1)
neural network
(1)
Papers
DropCompute: simple and more robust distributed synchronous training via compute variance reduction
NIPS 2023
Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
ICLR 2023
Neural gradients are near-lognormal: improved quantized and sparse training
ICLR 2021
Augment Your Batch: Improving Generalization Through Instance Repetition
CVPR 2020
At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?
ICLR 2020
The Knowledge Within: Methods for Data-Free Model Compression
CVPR 2020
The Implicit Bias of Gradient Descent on Separable Data
JMLR 2018
Norm matters: efficient and accurate normalization schemes in deep networks
NIPS 2018
Scalable methods for 8-bit training of neural networks
NIPS 2018
The Implicit Bias of Gradient Descent on Separable Data
ICLR 2018
Fix your classifier: the marginal value of training the last weight layer
ICLR 2018
Train longer, generalize better: closing the generalization gap in large batch training of neural networks
NIPS 2017