Learning with Temporal Point Processes

In recent years, there has been an increasing number of machine learning models and algorithms based on the theory of temporal point processes, which is a mathematical framework to model asynchronous event data. These models and algorithm have found a wide range of human-centered applications, from social and information networks and recommender systems to crime prediction and health. Moreover, this emerging line of research has already established connections to deep learning, deep generative models, Bayesian nonparametrics, causal inference, stochastic optimal control and reinforcement learning. However, despite these recent advances, learning with temporal point processes is still a relatively niche topic within the machine learning community---there are only a few research groups across the world with the necessary expertise to make progress. In this workshop, we aim to popularize temporal point processes within the machine learning community at large. In our view, this is the right time to organize such a workshop because, as algorithmic decisions becomes more consequential to individuals and society, temporal point processes will play a major role on the development of human-centered machine learning models and algorithms accounting for the feedback loop between algorithmic and human decisions, which are inherently asynchronous events. Moreover, it will be a natural follow up of a very successful and well-attended ICML 2018 tutorial on learning with temporal point processes, which two of us recently taught.