Assistant Professor, ECE Department, UCSB
Email: first name at ucsb dot edu
Office: HFH 3161
About Me
Before joining UCSB, I was a postdoctoral researcher at Harvard SEAS. I completed my Ph.D. and M.Eng. in Electrical and Computer Engineering at Carnegie Mellon University. I received B.S. in Electrical Engineering and Computer Science at KAIST. My research aims to develop theoretically-grounded tools for trustworthy and reliable machine learning systems by drawing ideas from different fields (e.g., Information Theory, Statistics, Machine Learning, Distributed Systems). For recent publications, see my Google Scholar page.
Keywords: Machine Learning, Ethical AI, Algorithmic Fairness, Information Theory, Differential Privacy, Distributed Computing, Fault-tolerant Computing
📣 I am hiring Ph.D. students and postdoc researchers. If you’re interested, send me an email with ‘[Prospective Student]’ in the subject line. Tell me why you are interested in my line of research. I won’t be able to respond to generic emails.
Teaching
- (Winter 2023) ‘ECE 594BB: Special Topics in Computer Engineering — Ethics of Machine Learning’. See the course website.
News
- (Nov 2022) We presented our work on “Beyond Adult and COMPAS: Fairness in Multi-Class Prediction” at Neurips 2022 (Selected for Oral!)
- (Nov 2022) I gave an invited talk at Sharing Colloquium at SNU on “Fair Machine Learning for Education: An Information Theorist’s Perspective”
- (Nov 2022) I gave an invited talk on “Fair Machine Learning for Education: An Information Theorist’s Perspective” at KAIST Graduate School of AI.
- (Sep 2022) I gave an invited talk on “Coding-theoretic Approach for Reliable Large-scale Machine Learning” at CNMAC 2022.
- (Sep 2022) I joined UCSB’s ECE department! ☀️🏝🤓
- (Jul 2022) I presented our paper on “Who Gets the Benefit of the Doubt? Racial Bias in Machine Learning Algorithms Applied to Secondary School Math Education” at the FATED 2022 workshop.
- (Jul 2022) I gave a tutorial on “Information-theoretic Tools for Responsible Machine Learning” at the Machine Learning/Reinforcement Learning Lecture Series hosted by The Korean Institute of Communications and Information Sciences.
- (Jun 2022) We organized a tutorial on “Information-theoretic Tools for Responsible Machine Learning“ at ISIT 2022.
- (Jun 2022) Ateet presented our work on “Differentially Private Distributed Matrix Multiplication: Fundamental Accuracy-Privacy Trade-Off Limits” at ISIT 2022.
- (Jun 2022) I presented our work on “Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values” at the 3rd annual Symposium on Foundations of Responsible Computing (FORC 2022)