Vijayalakshmi (Viji) Srinivasan
4 papers · 2019–2022 · 1 venue · 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 ↓
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
efficient computing
(2)
model compression
(2)
knowledge distillation
(1)
neural network optimization
(1)
distributed training
(1)
communication efficiency
(1)
deep neural network
(1)
gradient compression
(1)
low-precision training
(1)
training acceleration
(1)
structural sparsity
(1)
transformer model
(1)
gradient scaling
(1)
floating point
(1)
sparsified gradient
(1)
model quantization
(1)
Papers
Deep Compression of Pre-trained Transformer Models
NeurIPS 2022
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
NeurIPS 2020
Ultra-Low Precision 4-bit Training of Deep Neural Networks
NeurIPS 2020
Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks
NeurIPS 2019