I finished my PhD in Computer Science at CMU, where I was advised by Matt Fredrikson. My research was on privacy and fairness issues in machine learning. Prior to that, I studied math and computer science at MIT.
My last name is pronounced like the word "yum" (IPA: [jʌm]).
| syeom [at] cs.cmu.edu | |
| samuel-yeom |
| paper |
Avoiding Disparity Amplification under Different Worldviews Samuel Yeom and Michael Carl Tschantz ACM Conference on Fairness, Accountability, and Transparency, 2021 |
| paper arXiv |
Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness Samuel Yeom and Matt Fredrikson International Joint Conference on Artificial Intelligence, 2020 Note: The conference version has a minor error in the proof of Theorem 3. This is fixed in the arXiv version. |
| paper |
Learning Fair Representations for Kernel Models Zilong Tan, Samuel Yeom, Matt Fredrikson, and Ameet Talwalkar Conference on Artificial Intelligence and Statistics, 2020 |
|
paper code |
FlipTest: Fairness Testing via Optimal Transport Emily Black*, Samuel Yeom*, and Matt Fredrikson ACM Conference on Fairness, Accountability, and Transparency, 2020 |
| paper |
Overfitting, Robustness, and Malicious Algorithms: A Study of Potential Causes of Privacy Risk in Machine Learning Samuel Yeom, Irene Giacomelli, Alan Menaged, Matt Fredrikson, and Somesh Jha Journal of Computer Security, 2020 |
|
paper code |
Hunting for Discriminatory Proxies in Linear Regression Models Samuel Yeom, Anupam Datta, and Matt Fredrikson Advances in Neural Information Processing Systems, 2018 |
|
paper code |
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting Samuel Yeom, Irene Giacomelli, Matt Fredrikson, and Somesh Jha Distinguished Paper at the IEEE Computer Security Foundations Symposium, 2018 |
* Equal contribution
I was a TA for two courses at CMU:
I was an Officer in Puzzle Hunt CMU, which is a student club that runs a puzzle hunt every semester. Of the puzzles that I wrote, some of my favorites are: