Lecture 1: Randomize

Topics: randomized linear algebra, dimension reduction, and data visualization.

Lecture 2: Resample

Topics: computer age inference, simulation-based and resampling method.

Lecture 3: What If

Topics: causal inference in theory and practice, causal structural models, do-calculus, adjustments formula using supervised learning.

Lecture 4: No Regret

Topics: online algorithms and optimization, sequential investments, universal portfolios.

Lecture 5: Explore vs. Exploit I

Topics: sequential decision making, dynamic programming and its approximations, and reinforcement learning techniques including Q-learning and policy gradients.

Lecture 6: Explore vs. Exploit II

Topics: stochastic and adversarial bandits, upper confidence bound algorithm, explore-then-commit algorithm, exponential weight for exploration and exploitation algorithm.