๐Ÿ“š Trustworthy ML (2023 Fall)

Sep 5, 2023ยท
Sangdon Park
Sangdon Park
Walk the Talk + Midjourney

Trustworthy ML (AIGS703L / CSED703L)

As machine learning and deep learning models are impacting on real world environments (e.g., ChatGPT), concerns on the trustworthiness of machine-learned models are rising. In this course, we explore whether popular machine-learned models are trustworthy and then study various learning methods to enchant the models to be trustworthy. To this end, we will learn basic knowledge on machine learning theory, uncertainty learning via conformal prediction, adversarial examples/learning, machine unlearning, differentially private learning, fairness in learning, and miscellaneous topics on trustworthy generative AI.

Location

B2 Room 107

Instructor

Sangdon Park

Schedule (tentative)

Date
Topic
[Week 1] 9/5Trustworthy ML Introduction
[Week 1] 9/7Learning Theory: PAC learning
[Week 2] 9/12Learning Theory: Beyond PAC learning
[Week 2] 9/14Learning Theory: Beyond PAC learning
[Week 3] 9/19Learning Theory: Online learning
[Week 3] 9/21Learning Theory: Online learning
[Week 4] 9/26Learning Theory: Statistical Query
[Week 4] 9/28Korean Thanksgiving holiday
[Week 5] 10/3National Foundation Day
[Week 5] 10/5Uncertainty Learning: Conformal Prediction
[Week 6] 10/10Uncertainty Learning: PAC Conformal Prediction
[Week 6] 10/12Uncertainty Learning: Adaptive Conformal Prediction
[Week 7] 10/17Student Presentation 1
[Week 7] 10/19Adversarial Learning: Adversarial Example / Heuristic Adversarial Learning
[Week 8] 10/24Adversarial Learning: Certified Adversarial Learning
[Week 8] 10/26Machine Unlearning 1
[Week 9] 10/31Student Presentation 2
[Week 9] 11/2Machine Unlearning 2
[Week 10] 11/7Differential Privacy 1
[Week 10] 11/9Student Presentation 3
[Week 11] 11/14Student Presentation 3.5
[Week 11] 11/16Differential Privacy 2
[Week 12] 11/21Fairness in Learning 1
[Week 12] 11/23Fairness in Learning 2
[Week 13] 11/28Student Presentation 4
[Week 13] 11/30Student Presentation 5
[Week 14] 12/5Code Generation
[Week 14] 12/7Copyright
[Week 15] 12/12Student Presentation 6
[Week 15] 12/14Student Presentation 7
[Week 16] 12/19Student Presentation 8
[Week 16] 12/21Student Presentation 9