Pierre Stock
9 papers · 2018–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (5) π Academic Marathon (6) π Cross-Pollinator (12)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(16)
π
Conference Pioneer
Conferences
ICLR (4)
ICML (2)
ACL (1)
ECCV (1)
ICCV (1)
Top co-authors
Research topics
Keywords
differential privacy
(2)
federated learning
(1)
model quantization
(1)
image classification
(1)
vision transformer
(1)
attention mechanism
(1)
knowledge distillation
(1)
data-free distillation
(1)
neural network optimization
(1)
numerical optimization
(1)
mechanism design
(1)
communication efficiency
(1)
convolutional neural network
(1)
deep neural network
(1)
gradient compression
(1)
scaling law
(1)
privacy-utility trade-off
(1)
privacy budget
(1)
weight quantization
(1)
inference speed
(1)
Papers
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
ACL 2024
TAN Without a Burn: Scaling Laws of DP-SGD
ICML 2023
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
ICLR 2023
Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
ICML 2023
Training with Quantization Noise for Extreme Model Compression
ICLR 2021
LeViT: A Vision Transformer in ConvNet's Clothing for Faster Inference
ICCV 2021
And the Bit Goes Down: Revisiting the Quantization of Neural Networks
ICLR 2020
Equi-normalization of Neural Networks
ICLR 2019
ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
ECCV 2018