moran shkolnik
4 papers · 2020–2023 · 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
Venues
Top co-authors
Research topics
Keywords
neural network quantization
(1)
model compression
(1)
distributed training
(1)
gradient quantization
(1)
log-normal distribution
(1)
gradient sparsity
(1)
floating-point format
(1)
robust quantization
(1)
quantization policies
(1)
synchronous training
(1)
quantization policy
(1)
straggling worker
(1)
compute variance
(1)
neural gradient
(1)
Papers
DropCompute: simple and more robust distributed synchronous training via compute variance reduction
NeurIPS 2023
Neural gradients are near-lognormal: improved quantized and sparse training
ICLR 2021
Robust Quantization: One Model to Rule Them All
NeurIPS 2020
Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks
ECCV 2020