NTU Course
NewsHelpOverview

Prediction, Learning, and Games

Offered in 112-2

  • Serial Number

    84088

  • Course Number

    CSIE5002

  • Course Identifier

    922 U4550

  • No Class

  • 3 Credits

  • Elective

    Institute of Statistics and Data Science / DEPARTMENT OF COMPUTER SCIENCE & INFOR / GRADUATE INSTITUTE OF COMPUTER SCIENCE & INFORMATION ENGINEERING / GRADUATE INSTITUTE OF NETWORKING AND MULTIMEDIA

      Elective

    • Institute of Statistics and Data Science

    • DEPARTMENT OF COMPUTER SCIENCE & INFOR

    • GRADUATE INSTITUTE OF COMPUTER SCIENCE & INFORMATION ENGINEERING

    • GRADUATE INSTITUTE OF NETWORKING AND MULTIMEDIA

  • YEN-HUAN LI
  • Thu 7, 8, 9

  • 資110

  • Type 3

  • 20 Student Quota

    NTU 20

  • No Specialization Program

  • Chinese
  • NTU COOL
  • Core Capabilities and Curriculum Planning
  • Notes
    Theory course, requiring math maturity.

  • NTU Enrollment Status

    Enrolled
    0/20
    Other Depts
    0/0
    Remaining
    0
    Registered
    0
  • Course Description
    This is a *theory* course. There will not be any programming assignment. The students will have to read and write mathematical proofs. Will it rain tomorrow? Will the stock price go down tomorrow? How likely will the sun rise tomorrow? Such problems can be reduced to a very basic problem: Given a sequence of bits, on which there is not any probabilistic model, how likely will the next bit be 1? In this course, we will study this problem and its extensions from several aspects. The topics include Blackwell approachability, PAC-Bayes analysis, probability forecasting with the logarithmic loss, online portfolio selection, and learning with expert advice.
  • Course Objective
    After taking this course, the students are expected to - be familiar with basic concepts about Blackwell approachability and the aggregating algorithm and - be able to read related literature.
  • Course Requirement
    - The students are expected to be motivated enough. - The students are expected to be familiar with multivariate calculus, probability, and linear algebra. Knowledge of machine learning and statistics may be helpful but are not necessary.
  • Expected weekly study hours after class
  • Office Hour
  • Designated Reading
  • References
    - N. Cesa-Bianchi & G. Lugosi. Prediction, Learning, and Games. 2006. - J.-F. Mertens et al. Repeated Games. 2015.
  • Grading
  • Adjustment methods for students
  • Course Schedule