|
課程名稱 |
預測、學習、與賽局
Prediction, Learning, and Games |
|
開課學期 |
110-2 |
|
授課對象 |
電機資訊學院 資訊網路與多媒體研究所 |
|
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 |
星期四7,8,9(14:20~17:20) |
|
上課地點 |
資105 |
|
備註 |
Theory course, requiring math maturity.
總人數上限：20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: the "uncertainty" we face in real life typically does not follow any probabilistic model and can be adversarial. This course introduces online learning theory, whose probability-free nature naturally avoids the aforementioned theory-practice gap.
We will mainly focus on algorithms for individual sequence prediction, i.e., predicting a binary sequence without any probabilistic model. If time allows, we will also study online portfolio selection, learning with expert advice, online convex optimization, and learning in games.
====
[Course registration information]
This is a "type-3" course ( 第三類加簽 ). Please try your luck during the "online course add period". |
|
課程目標 |
本課程的目標在於讓修課同學：
● Be able to think beyond the statistical and PAC learning frameworks.
● Be able to read state-of-the-art literature on learning theory.
● Be able to analyze basic online (learning) algorithms. |
|
課程要求 |
Prerequisites: Knowledge in calculus, linear algebra, and probability are necessary. Math maturity and interest in theory are required.
Knowledge in convex optimization, learning theory, 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. 2018. Introduction to multi-armed bandits.
9. T. Lattimore and C. Szepesvari. 2018. Bandit Algorithms. |
|
評量方式
(僅供參考) |
|
No. |
項目 |
百分比 |
說明 |
|
1. |
Short reports |
60% |
Expositions of online learning concepts assigned by the lecturer that are not covered in the course. |
2. |
Final project & presentation |
40% |
Oral presentation of a survey on an online learning topic or your own novel research results (self-plagiarism is not allowed). |
|
|