GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training

Mingchao Yu, Zhifeng Lin, Krishna Narra, Songze Li, Youjie Li, Nam Sung Kim, Alexander Schwing, Murali Annavaram, Salman Avestimehr

Nov-20-2025, 20:11:32 GMT–Neural Information Processing Systems

Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation.

gradient, gradiv eq, iteration, (11 more...)

Neural Information Processing Systems

Nov-20-2025, 20:11:32 GMT

Conferences PDF

Country:
- North America
  - Canada
    - Ontario > Toronto (0.04)
    - Quebec > Montreal (0.04)
  - United States
    - California (0.14)
    - Illinois (0.04)

Industry:
- Government > Regional Government (0.46)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.49)

Duplicate Docs Excel Report

Title
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training

Similar Docs Excel Report more

Title	Similarity	Source
None found