Bayesian Computation in Marketing
Interschool Reading Group
The Bayesian Computation in Marketing Interschool Reading Group brings together academic marketers with research interests in Bayesian computation and statistical machine learning to read and discuss recent advances in methodology, both within marketing, and in related fields including statistics and computer science. Each virtual meeting focuses on a specific paper, or a set of related papers, with the discussion led "presentation-style" by a group member. The group is organized by Ryan Dew and Longxiu Tian.
Membership is limited to junior faculty and Ph.D. students in Marketing, who have active research involving Bayesian computation and statistical (probabilistic) machine learning. All members must be willing to read papers and lead the discussion when it is their turn. Because we will focus on reading methodological papers, members should have familiarity with the fundamentals of Bayesian and probabilistic graphical modeling, Bayesian inference and computation (including MCMC and variational inference methods), and basic machine learning technologies like neural networks.
Meeting Schedule and Topics
Possible topics include advances in inference methods and generative modeling, Bayesian nonparametrics and kernel methods, Bayesian neural networks, experimental design, reinforcement learning, recommendation systems, models of unstructured data, computational approaches to causal inference, and more. All meetings will take place virtually. A link will be sent to members before each meeting.
Upcoming readings / topics:
The Blessings of Multiple Causes
Counterfactual Reasoning and Learning Systems
Adapting Neural Networks for the Estimation of Treatment Effects
Deep Neural Networks for Estimation and Inference
Causal Inference for Recommender Systems
An Overview of Robust Bayesian Analysis
Robust Bayesian Inference via Coarsening
Covariances, Robustness, and Variational Bayes
Counterfactual Inference for Consumer Choice Across Many Product Categories
Introduction to VAEs
Causal Effect Inference with Deep Latent Variable Models
Black-box Variational Inference
Variational Inference with Normalizing Flows
Decision-making with VAEs
Disentangled representation learning