Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference.
Alessandro SordoniXingdi YuanMarc-Alexandre CôtéMatheus PereiraAdam TrischlerZiang XiaoArian HosseiniFriederike NiedtnerNicolas Le RouxPublished in: CoRR (2023)
Keyphrases
- variational inference
- bayesian inference
- gaussian process
- variational methods
- topic models
- mixture model
- posterior distribution
- probabilistic model
- least squares
- probabilistic graphical models
- training set
- closed form
- exponential family
- graphical models
- latent dirichlet allocation
- natural language
- regression model
- cross validation
- information retrieval
- supervised learning
- image sequences