Fall 2018

Tentative Topics:

  • Online Learning Theory
    • Prediction with Expert Advice
    • Randomized Greed
    • Regret
    • Weighted Majority Algorithm
  • Online Classification
    • Online Perceptron
    • Online Winnow Algorithm
    • Online SVM
  • Online Convex Optimization
    • Follow the Regularized Leader
    • Online Gradient Descent
    • Exponential Gradient and Sparsity
  • Bandits
  • Supervised Learning
    • Gradient Boosting
    • Gaussian Processes
    • Non-linear Kernel Methods
  • Adversarial Learning
    • Matrix Games, Minimax
    • Data Augmentation
    • Inverse Reinforcement Learning (MaxEnt, Max-Margin, GAN)
  • Graphical Models
    • Random Fields
    • Bayesian Estimation
    • Kalman Filtering
    • Hidden Markov Models
    • Particle Filtering