Jonathan Frankle
17 papers · 2019–2024 · 5 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 ↑
🗺️ Taxonomy Completionist (27) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
👑
Triple Crown
🏆
Keyword Champion
(2)
❓
The Questioner
(3)
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(53)
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(14)
Optimization & Theory · Machine Learning
(12)
Deep Learning
(11)
Techniques
(9)
Artificial Intelligence
(6)
Core AI
(5)
Application Areas
(4)
Natural Language Processing
(3)
Architectures
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory · Deep Learning
(3)
Resources & Methods
(3)
Learning Paradigms
(2)
Computer Vision
(1)
Keywords
neural network pruning
(7)
lottery ticket hypothesis
(6)
sparse training
(4)
model compression
(4)
neural network optimization
(3)
iterative magnitude pruning
(3)
transfer learning
(3)
self-supervised learning
(2)
loss landscape
(2)
masked language modeling
(2)
magnitude pruning
(2)
network initialization
(2)
network pruning
(2)
network compression
(2)
convolutional neural network
(1)
diffusion model
(1)
model pruning
(1)
attention mechanism
(1)
weight pruning
(1)
text-to-image generation
(1)
Papers
Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
ICML 2024
CommonCanvas: Open Diffusion Models Trained on Creative-Commons Images
CVPR 2024
Dynamic Masking Rate Schedules for MLM Pretraining
EACL 2024
MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining
NeurIPS 2023
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
ICLR 2023
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks
NeurIPS 2022
Pruning’s Effect on Generalization Through the Lens of Training and Regularization
NeurIPS 2022
What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?
ICML 2022
On the Predictability of Pruning Across Scales
ICML 2021
Pruning Neural Networks at Initialization: Why Are We Missing the Mark?
ICLR 2021
The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models
CVPR 2021
Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs
ICLR 2021
Comparing Rewinding and Fine-tuning in Neural Network Pruning
ICLR 2020
Linear Mode Connectivity and the Lottery Ticket Hypothesis
ICML 2020
The Early Phase of Neural Network Training
ICLR 2020
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
NeurIPS 2020
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
ICLR 2019