Charlie Hou

I am a fourth year Ph.D. student at Carnegie Mellon University advised by Giulia Fanti. My main research interest is in Federated Learning (FL). I like to think about finding solutions to problems that plague FL in production use cases while still protecting user privacy. Outside of FL, I am broadly interested in (and have experience working on) self-supervised learning, representation learning, learning-to-rank (ranking), NLP, CV, transformer models, deep learning, and optimization.

Before I started at CMU, I did my undergrad at Princeton University, where I worked with Yuxin Chen and Miklos Racz.

Google Scholar, Github, LinkedIn, CV

Contact me at [charlieh at andrew dot cmu dot edu].


Google Collabs Research Award ($70k grant and up to $20k in GCP credits) 2022.
With Giulia Fanti and Sewoong Oh
Tiger Chef Champion, 2018


FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning
Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh
ICLR 2022, Oral Presentation at ICML-FL workshop 2021
Efficient Algorithms for Federated Saddle Point Optimization
Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh
SquirRL: Automating Attack Analysis on Blockchain Incentive Mechanisms with Deep Reinforcement Learning
Charlie Hou*, Mingxun Zhou*, Yan Ji, Phil Daian, Florian Tramer, Giulia Fanti, Ari Juels (*equal contribution)
NDSS 2021

Work Experience

Meta (formerly Facebook) Reality Labs, Research Intern. Topic: Federated Learning for Language Models.
Redmond, WA, Fall 2022
Amazon Search (A9), Applied Science Intern. Topic: Self-supervised learning for Learning-to-rank.
Palo Alto, CA, Summer 2022
Amazon, Applied Science Intern. Topic: Sub-same day delivery optimization.
Seattle, WA, Summer 2021
Uber ATG (Advanced Technologies Group), Research Intern. Topic: Deep Radar Simulation.
San Francisco, CA, Summer 2019

Professional Service

Reviewer, ICLR 2023
Student Volunteer at STOC 2020