Course Schedule

8/31 No Class	9/02 Course Overview
9/07 Maximum Likelihood Estimators & Convex Optimization	9/09 Bayesian Models HW #0 Due
9/15 Bayesian versus Frequentist Approaches	9/16 Introduction to Sampling HW #1 Due
9/21 Monte Carlo Simulation	9/23 MCMC Sampling HW #2 Due
9/28 MCMC Sampling: Diagnostics	9/30 Latent Variable Models & EM Project Checkpoint #1: Team Formation HW #3 Due
10/05 Latent Variable Models & VI	10/07 Hierarchical Models, Empirical Bayes & Model Selection HW #4 Due
10/12 Logistic Regression & Gradient Descent	10/14 Stochastic Gradient Descent & Simulated Annealing HW #5 Due
10/19 Hamiltonian Monte Carlo	10/21 Parallel Tempering Project Checkpoint #2: Paper Selection HW #6 Due
10/26 Neural Networks	10/28 Bayesian Neural Networks (BNNs) and VI HW #7 Due
11/02 Automatic Differentiation Variational Inference	11/04 Evaluating Variational Inference Project Checkpoint #3: Paper Overview HW #8 Due
11/09 Variational Autoencoders (VAEs)	11/10 VAEs: Implementation Details
11/16 Application of Deep Learning: Representation Learning	11/18 Application of VAEs: Counterfactual Explanations and Recourse Project Checkpoint #4: Pedagogical Experiments
11/23 Application of Uncertainty Quantification	11/25 Holiday
11/30 Human-in-the-loop Learning and Socio-technical Systems	12/02 Ethics and Interpretability in Machine Learning Project Due: December 17th