課程資訊
課程名稱
 預測、學習、與賽局
Prediction, Learning, and Games 
開課學期
 108-2 
授課對象
 理學院  數學系  
授課教師
 李彥寰 
課號
 CSIE5002 
課程識別碼
 922 U4550 
班次
  
學分
 3.0 
全/半年
 半年 
必/選修
 選修 
上課時間
 星期一7,8,9(14:20~17:20) 
上課地點
 資105 
備註
 Theory course, requiring math maturity.
總人數上限：40人 
  
課程簡介影片
 
核心能力關聯
 核心能力與課程規劃關聯圖
課程大綱
為確保您我的權利,請尊重智慧財產權及不得非法影印
課程概述

*This is an advanced course in learning theory.*

The probably approximately correct (PAC) theory has been the standard framework of machine learning for decades, but its underlying “i.i.d. data” assumption results in a significant theory-practice gap. This course introduces online learning theory, whose probability-free nature naturally avoids the aforementioned theory-practice gap. The main focuses are:
- PAC learning theory
- Individual sequence prediction.
- Learning with expert advice and the aggregating algorithm.
- Advanced decision theoretic online learning.
The tentative schedule can be found below.

The exact contents of this course may change with respect to the latest advances
in learning theory.

Course website: https://cool.ntu.edu.tw/courses/752 

課程目標
 本課程的目標在於讓修課同學：
● Be able to read state-of-the literature on learning theory.
● Be able to analyze basic online (learning) algorithms.
● Be able to work on online learning research topics.
● Be able to think beyond the statistical and PAC learning frameworks. 
課程要求
 Prerequisites: Calculus, linear algebra, and probability.

Knowledge in convex optimization, machine learning, and/or statistics can be helpful but not necessary. 
預期每週課後學習時數
  
Office Hours
  
指定閱讀
 待補 
參考書目
 1. N. Cesa-Bianchi and G. Lugosi. 2006. Prediction, Learning, and Games.
2. S. Shalev-Shwartz. 2011. Online Learning and Online Convex Optimization.
3. S. Bubeck. 2011. Introduction to Online Optimization.
4. V. V. V’yugin. 2012. Lecture Notes on Machine Learning and Prediction.
5. S. Hart and A. Mas-Colell. 2013. Simple Adaptive Strategies.
6. A. Rakhlin and K. Sridharan. 2014. Statistical Learning and Sequential Prediction.
7. E. Hazan. 2015. Introduction to Online Convex Optimization.
8. A. Slivkins. 2019. Introduction to multi-armed bandits.
9. T. Lattimore and C. Szepesvari. 2019. Bandit Algorithms. 
評量方式
(僅供參考)
  
No.
項目
百分比
說明
1. 
 Homework 
60% 
 Four assignments. 15% each.  
2. 
 Final project 
40% 
 Report (and oral presentation if time allowed). Find a paper that is not entirely correct and discuss the paper's significance and how to fix the errors.  
 
課程進度
週次
日期
單元主題
第1週
 3/02  Course organization. PAC learning.  
第2週
 3/09  More complexity measures in PAC learning 
第3週
 3/16  PAC-Bayes analysis 
第4週
 3/23  Individual sequence prediction 
第5週
 3/30  Individual sequence prediction 
第6週
 4/06  Individual sequence prediction 
第7週
 4/13  Individual sequence prediction 
第8週
 4/20  Aggregating algorithm 
第9週
 4/27  Aggregating algorithm 
第10週
 5/04  No class.  
第11週
 5/11  Midterm.  
第12週
 5/18  Online gradient descent.  
第13週
 5/25  Decision theoretic online learning.  
第14週
 6/01  Quantile bounds.  
第15週
 6/08  Second-order and adaptive bounds.  
第16週
 6/15  Final project presentations.  
第17週
 6/22  Final project. 
第18週
 6/29  Final project.