We'll discuss the use of generative modeling, in particular, generative adversarial networks (GANs), as a potential tool for speeding up expensive theoretical models and simulations in scientific and engineering applications. In particular, we'll show that GANs can learn high-energy particle physics by example - that is, we're able to generate physically meaningful processes from an end-to-end trained deep generative network. Our model presents a speedup of 200x using GPUs over the fastest current particle generation software. We'll walk through architectural choices given a very sparse domain, introduce a new dataset for benchmarking generative models, and discuss model evaluation for generative models in high-energy particle physics. Finally, we'll discuss future work in both high-energy particle physics and beyond.