2017/01/13 by Dustin Tran, Matthew D. Hoffman, Tran, Dustin +9 · 4 voices · 8 citations
Computer Science · #Adversarial Robustness in Machine Learning #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #cs.AI #cs.LG #cs.PL #stat.CO #stat.ML
paper · pdf · doi:10.48550/arxiv.1701.03757
openalex publication_date 2017/01/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose Edward, a Turing-complete probabilistic programming language. Edward defines two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as traditional deep learning. For flexibility, Edward makes it easy to fit the same model using a variety of composable inference methods, ranging from point estimation to variational inference to MCMC. In addition, Edward can reuse the modeling representation as part of inference, facilitating the design of rich variational models and generative adversarial networks. For efficiency, Edward is integrated into TensorFlow, providing significant speedups over existing probabilistic systems. For example, we show on a benchmark logistic regression task that Edward is at least 35x faster than Stan and 6x faster than PyMC3. Further, Edward incurs no runtime overhead: it is as fast as handwritten TensorFlow.