Machine Learning Theory(1)

1. What is ML

2. History

3. Subfield

• Supervised Learning
• Unsupervised Learning
• Online learning
• Interactive Learning
• Graphical Models
• RL
• DL

4. Foundation of (supervised) learning

1. collecting training data $$(x_i,y_i)$$

2. learn a mapping F from X to Y based on training data[design a learning algorithm]

3. test(prediction):F(x)

   Assumption: training test Independently identical distribution

   $$f^{\ast }(x)=argma{x}_{y}P(y|x)$$

5. books

1. Learning Theory

   Foundations of Machine Learning

   Understanding Machine Learning: From Theory to Algorithm

2. Optimization

   Convex Optimization Algorithm and Complexity

3. RL

   Reinforcement Learning David Silver

4. Graphical Models

   Probabilistic graphical models Koller

robert schapire

peter bartlett