Charbel Sakr
5 papers · 2017–2024 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🗺️
Taxonomy Completionist
(10)
Venues
Top co-authors
Research topics
Keywords
model compression
(4)
numerical precision
(2)
model quantization
(1)
neural network training
(1)
matrix factorization
(1)
optimal transport
(1)
neural network optimization
(1)
gradient estimation
(1)
tensor decomposition
(1)
deep learning training
(1)
deep neural network
(1)
quantization-aware training
(1)
magnitude-aware differentiation
(1)
clipping threshold
(1)
newton-raphson method
(1)
low precision
(1)
backpropagation algorithm
(1)
large language model
(1)
network quantization
(1)
fixed point quantization
(1)
Papers
ESPACE: Dimensionality Reduction of Activations for Model Compression
NeurIPS 2024
Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
ICML 2022
Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks
ICLR 2019
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm
ICLR 2019
Analytical Guarantees on Numerical Precision of Deep Neural Networks
ICML 2017