Abstract

Speaker 1: Konstantina Palla (MSR Cambridge). Title: Bayesian nonparametrics for Sparse Dynamic Networks. Abstract: We propose a Bayesian nonparametric prior for time-varying networks. To each node of the network is associated a positive parameter, modelling the sociability of that node. Sociabilities are assumed to evolve over time and are modelled via a dynamic point process model. The model is able to (a) capture smooth evolution of the interaction between nodes, allowing edges to appear/disappear over time (b) capture long term evolution of the sociabilities© and yield sparse graphs, where the number of edges grows subquadratically with the number of nodes. The evolution of the sociabilities is described by a tractable time-varying gamma process. We provide some theoretical insights into the model and apply it to real world datasets.

Speaker 2: Mark Rowland (Cambridge university). Title: Analysing Distributional Reinforcement Learning. Abstract: Distributional approaches to value-based reinforcement learning use the entire distribution of returns, rather than just their expected values. Recently, these methods have been shown to yield state-of-the-art performance on a variety of RL tasks. In this talk, I’ll recap some of the main algorithms and results in distributional reinforcement learning, and give an overview of some recent theoretical developments (joint work with Marc G. Bellemare, Will Dabney, Rémi Munos, and Yee Whye Teh).