arXiv · 1711.07724
Using stochastic computation graphs formalism for optimization of sequence-to-sequence model
Abstract
Variety of machine learning problems can be formulated as an optimization task for some (surrogate) loss function. Calculation of loss function can be viewed in terms of stochastic computation graphs (SCG). We use this formalism to analyze a problem of optimization of famous sequence-to-sequence model with attention and propose reformulation of the task. Examples are given for machine translation (MT). Our work provides a unified view on different optimization approaches for sequence-to-sequence models and could help researchers in developing new network architectures with embedded stochastic nodes.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Eugene Golikov, Vlad Zhukov, Maksim Kretov. 2017-12-15. Using stochastic computation graphs formalism for optimization of sequence-to-sequence model. https://arxiv.org/abs/1711.07724
Cite the original work for its findings. Save a collection to share your selection of sources.