2022년도 1학기 컴퓨터공학특강:기계학습을 위한 최적화 (CSED490Y-01) 강의계획서

1. 수업정보

학수번호 CSED490Y 분반 01 학점 3.00
이수구분 전공선택 강좌유형 강의실 강좌 선수과목
포스테키안 핵심역량
강의시간 월, 수 / 11:00 ~ 12:15 / 제2공학관 강의실 [106호] 성적취득 구분 G

2. 강의교수 정보

이남훈 이름 이남훈 학과(전공) 인공지능대학원
이메일 주소 namhoonlee@postech.ac.kr Homepage https://namhoonlee.github.io/
연구실 HTTPS://NAMHOONLEE.GITHUB.IO/ 전화 054-279-2393
Office Hours Thursdays 5-6pm (by appointment)

3. 강의목표

This course offers introductory lectures on the fundamental ideas in mathematical optimization for machine learning. Students will also perform a small group project throughout the course. By covering both theory and practice, this course aims to help students get solid understanding and computational skills in optimization methods used for machine learning.

4. 강의선수/수강필수사항

There are no formal prerequisites required to take this course, but ideally if you have some background in the following it will significantly help your learning experience:
- good knowledge in mathematics including linear algebra, calculus, and probability
- basic skills for scientific and numerical computing
- exposure to machine learning and artificial intelligence
Both undergraduate and graduate students are welcome to take this course.

5. 성적평가

- Participation and discussion: 5%
- Quizzes: 15%
- Midterm exam: 40%
- Final project: 40%

6. 강의교재

도서명 저자명 출판사 출판년도 ISBN
There is no textbook required for this course, but you may find the books listed in the references below useful for your study throughout this course. 0000

7. 참고문헌 및 자료

- Convex Optimization, Stephen Boyd and Lieven Vandenberghe
- Convex Optimization: Algorithms and Complexity, Sebastien Bubeck
- Numerical Optimization, Jorge Nocedal and Stephen J. Wright
- Introductory Lectures on Convex Optimization: A Basic Course, Yurii Nesterov
- Machine Learning: A Probabilistic Perspective, Kevin P. Murphy
- Pattern Recognition and Machine Learning, Christopher Bishop

8. 강의진도계획

1. Introduction
2. Basics of machine learning and optimization
3. Convex optimization
4. Gradient descent
5. Subgradient and projected gradient methods
6. Proximal gradient descent
7. Stochastic gradient descent
8. Midterm week (no class)
9. Second order methods
10. Accelerated methods
11. Variance reduced methods
12. Adaptive gradient methods
13. Distributed optimization
14. Advanced topics
15. Project presentations
16. Final week (no class)

9. 수업운영

- The lectures will be delivered online due to the COVID related situation.
- The quizzes will take place without notice.
- The midterm exam must be taken offline on campus.
- The project is a team effort as a group of up to three students.

10. 학습법 소개 및 기타사항

The plan outlined in the syllabus is subjected to change due to unforeseen circumstances.

11. 장애학생에 대한 학습지원 사항

- 수강 관련: 문자 통역(청각), 교과목 보조(발달), 노트필기(전 유형) 등

- 시험 관련: 시험시간 연장(필요시 전 유형), 시험지 확대 복사(시각) 등

- 기타 추가 요청사항 발생 시 장애학생지원센터(279-2434)로 요청