conftrace_

stochastic quantization

7 papers

Explore in graph

Also known as

SQ

Co-occurring keywords · papers mentioning both

communication compression (2) model compression (2) runtime complexity (1) adaptive quantization (1) newton-type method (1) fair representation learning (1) binary neural network (1) vector quantized variational autoencoder (1) gradient sparsification (1) expert parallelism (1)

Papers

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