Jonathan Frankle
17 papers · 2019–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Academic Marathon (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (5) π£ Hot Topic Early Bird
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Conference Polyglot
(5)
π
Triple Crown
π₯
Unstoppable
(6)
β
The Questioner
(3)
π
Century Club
(17)
Conferences
ICLR (6)
ICML (4)
NIPS (4)
CVPR (2)
EACL (1)
Top co-authors
Keywords
lottery ticket hypothesis
(4)
neural network pruning
(3)
model compression
(3)
transfer learning
(3)
neural network optimization
(3)
sparse training
(3)
network pruning
(2)
masked language modeling
(2)
loss landscape
(2)
iterative magnitude pruning
(2)
diffusion model
(1)
scaling law
(1)
model generalization
(1)
linear mode connectivity
(1)
masking rate
(1)
self-supervised pre-training
(1)
transformer encoder
(1)
network initialization
(1)
unstructured pruning
(1)
network compression
(1)
Papers
Dynamic Masking Rate Schedules for MLM Pretraining
EACL 2024
CommonCanvas: Open Diffusion Models Trained on Creative-Commons Images
CVPR 2024
Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
ICML 2024
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
ICLR 2023
MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining
NIPS 2023
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks
NIPS 2022
What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?
ICML 2022
Pruningβs Effect on Generalization Through the Lens of Training and Regularization
NIPS 2022
The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models
CVPR 2021
Pruning Neural Networks at Initialization: Why Are We Missing the Mark?
ICLR 2021
Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs
ICLR 2021
On the Predictability of Pruning Across Scales
ICML 2021
Comparing Rewinding and Fine-tuning in Neural Network Pruning
ICLR 2020
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
NIPS 2020
The Early Phase of Neural Network Training
ICLR 2020
Linear Mode Connectivity and the Lottery Ticket Hypothesis
ICML 2020
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
ICLR 2019