conftrace_

stochastic quantization

7 papers

Explore in graph

Also known as

SQ

Co-occurring keywords

communication compression (55) model compression (3302) runtime complexity (2) adaptive quantization (8) newton-type method (7) fair representation learning (19) binary neural network (75) vector quantized variational autoencoder (20) gradient sparsification (16) expert parallelism (4)

Papers

RCMoE: A Communication-Efficient Random Compression Framework for Resource-Constrained Mixture-of-Experts Training AAAI 2026
Optimal and Approximate Adaptive Stochastic Quantization NIPS 2024
Invariant Representations with Stochastically Quantized Neural Networks AAAI 2023
Correlated Quantization for Distributed Mean Estimation and Optimization ICML 2022
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization ICML 2022
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning ICML 2022
ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning ICML 2017