Charlie Hou

Joined

May 2021

Names

Charlie Hou (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

CMU, Carnegie Mellon University (andrew.cmu.edu)

2019 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Present

Coauthor

Kiran K. Thekumparampil

Present

Coauthor

Present

Expertise

Federated Learning

Present

Streaming

Present

Reinforcement Learning

Present

Publications

Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
Shuqi Ke, Charlie Hou, Sewoong Oh, Giulia Fanti
- Accepted by TMLR
- Readers: Everyone
Private Federated Learning using Preference-Optimized Synthetic Data
Charlie Hou, Mei-Yu Wang, Yige Zhu, Daniel Lazar, Giulia Fanti
- ICLR 2025 Workshop SynthData
- Readers: Everyone
Private Federated Learning using Preference-Optimized Synthetic Data
Charlie Hou, Mei-Yu Wang, Yige Zhu, Daniel Lazar, Giulia Fanti
- ICML 2025 poster
- Readers: Everyone
Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
Shuqi Ke, Charlie Hou, Sewoong Oh, Giulia Fanti
- FITML 2024 Poster
- Readers: Everyone
Characterizing the Training Dynamics of Private Fine-tuning with Langevin Diffusion
Shuqi Ke, Charlie Hou, Sewoong Oh, Giulia Fanti
- Submitted to ICLR 2025
- Readers: Everyone
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky, Giulia Fanti, Yesh Dattatreya, sujay sanghavi
- Accepted by TMLR
- Readers: Everyone
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky, Giulia Fanti, sujay sanghavi
- 2nd SPIGM @ ICML Poster
- Readers: Everyone
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
Charlie Hou, Akshat Shrivastava, Hongyuan Zhan, Rylan Conway, Trang Le, Adithya Sagar, Giulia Fanti, Daniel Lazar
- PML
- Readers: Everyone
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
Charlie Hou, Akshat Shrivastava, Hongyuan Zhan, Rylan Conway, Trang Le, Adithya Sagar, Giulia Fanti, Daniel Lazar
- ICML 2024 Oral
- Readers: Everyone
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky, Giulia Fanti, Yesh Dattatreya, sujay sanghavi
- 29 Sept 2023 (modified: 29 Sept 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone

View all 15 publications

Co-Authors