Hongzhou Lin

Applied Scientist, Amazon

Joined

August 2018

Names

Hongzhou Lin (Preferred)

Emails

****@inria.fr (Confirmed)

****@mit.edu (Confirmed)

****@gmail.com (Confirmed)

****@amazon.com (Confirmed)

Personal Links

DBLP

Career & Education History

Applied Scientist

Amazon (amazon.com)

2020 – Present

Postdoc

Massachusetts Institute of Technology (mit.edu)

2018 – 2020

PhD student

INRIA (inria.fr)

2014 – 2017

Advisors, Relations & Conflicts

Postdoc Advisor

Stefanie Jegelka

2018 – 2020

PhD Advisor

Julien Mairal

2014 – 2017

PhD Advisor

Zaid Harchaoui

2014 – 2017

Expertise

deep learning

2018 – 2019

optimization

2015 – 2019

Publications

Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
Yong Lin, Shange Tang, Bohan Lyu, Ziran Yang, Jui-Hui Chung, Haoyu Zhao, Lai Jiang, Yihan Geng, Jiawei Ge, Jingruo Sun, Jiayun Wu, Jiri Gesi, Ximing Lu, David Acuna, Kaiyu Yang, Hongzhou Lin, Yejin Choi, Danqi Chen, Sanjeev Arora, Chi Jin
- ICLR 2026 Poster
- Readers: Everyone
QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
Jiazheng Li, Hongzhou Lin, Hong Lu, Kaiyue Wen, Zaiwen Yang, Jiaxuan Gao, Yi Wu, Jingzhao Zhang
- ICLR 2026 Poster
- Readers: Everyone
Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving of Inequalities
Haoyu Zhao, Yihan Geng, Shange Tang, Yong Lin, Bohan Lyu, Hongzhou Lin, Chi Jin, Sanjeev Arora
- NeurIPS 2025 Datasets and Benchmarks Track poster
- Readers: Everyone
Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
Yong Lin, Shange Tang, Bohan Lyu, Jiayun Wu, Hongzhou Lin, Kaiyu Yang, Jia LI, Mengzhou Xia, Danqi Chen, Sanjeev Arora, Chi Jin
- COLM 2025
- Readers: Everyone
Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?
Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen, Hongzhou Lin, Jingzhao Zhang, Mikhail Belkin
- ICML 2025 poster
- Readers: Everyone
From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
Kaiyue Wen, Huaqing Zhang, Hongzhou Lin, Jingzhao Zhang
- M3L Poster
- Readers: Everyone
From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
Kaiyue Wen, Huaqing Zhang, Hongzhou Lin, Jingzhao Zhang
- ICLR 2025 Poster
- Readers: Everyone
Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning
Ligeng Zhu, Hongzhou Lin, Yao Lu, Yujun Lin, Song Han
- Published: 09 Nov 2021, Last Modified: 31 Oct 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Stochastic Optimization with Non-stationary Noise: The Power of Moment Estimation
Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie
- 28 Sept 2020 (modified: 12 Oct 2025)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
ResNet with one-neuron hidden layers is a Universal Approximator
Hongzhou Lin, Stefanie Jegelka
- 2018 (modified: 11 Nov 2022)
- NeurIPS 2018
- Readers: Everyone

View all 11 publications

Co-Authors

View all 41 co-authors