Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models.

Yongxin Guo Zhenglin Cheng Xiaoying Tang Tao Lin

Published in: CoRR (2024)

Keyphrases

probabilistic model
model selection
cost effective
fuzzy logic
markov random field
exponential family
decision trees
artificial neural networks
dynamic environments
parameter estimation
linear dynamical systems