Haochen Zhang

Image

Email: jhaochen [at] cs.stanford.edu

Google Scholar  |  LinkedIn

About

I'm currently a Member of Technical Staff at Anthropic.

Previously, I was a PhD student in Computer Science at Stanford University, affiliated with Stanford AI Lab. I was fortunate to be advised by Tengyu Ma. My research focuses on deep learning theory, representation learning, and optimization.

In the past, I've also had the opportunity to work with Suvrit Sra on convex optimization, and with Roger Grosse on optimization for neural networks.

Before Stanford, I was an undergraduate at Yao Class led by Professor Andrew Chi-Chih Yao at Tsinghua University.

Research
Publish under name Jeff Z. HaoChen
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
Arvind Mahankali*, Jeff Z. HaoChen*, Kefan Dong, Margalit Glasgow, Tengyu Ma
NeurIPS, 2023 [PDF]
Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models
Yuhui Zhang, Michihiro Yasunaga, Zhengping Zhou, Jeff Z. HaoChen, James Zou, Percy Liang, Serena Yeung
ACL, 2023 [PDF]
A Theoretical Study of Inductive Biases in Contrastive Learning
Jeff Z. HaoChen, Tengyu Ma
ICLR, 2023 [PDF]
Diagnosing and Rectifying Vision Models using Language
Yuhui Zhang, Jeff Z. HaoChen, Shih-Cheng Huang, Kuan-Chieh Wang, James Zou, Serena Yeung
ICLR, 2023 [PDF]
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
Jeff Z. HaoChen, Colin Wei, Ananya Kumar, Tengyu Ma
NeurIPS, 2022 [PDF]
Amortized Proximal Optimization
Juhan Bae, Paul Vicol, Jeff Z. HaoChen, Roger Grosse
NeurIPS, 2022 [PDF]
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
Kendrick Shen, Robbie Jones, Ananya Kumar, Sang Michael Xie, Jeff Z. HaoChen, Tengyu Ma, Percy Liang
ICML, 2022 [PDF]
Self-supervised Learning is More Robust to Dataset Imbalance
Hong Liu, Jeff Z. HaoChen, Adrien Gaidon, Tengyu Ma
ICLR, 2022 (spotlight) [PDF]
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss
Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma
NeurIPS, 2021 (oral) [PDF]
Shape Matters: Understanding the Implicit Bias of the Noise Covariance
Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma
COLT, 2021 [PDF]
Meta-learning Transferable Representations with a Single Target Domain
Hong Liu, Jeff Z. HaoChen, Colin Wei, Tengyu Ma
Preprint, 2020 [PDF]
Random Shuffling Beats SGD after Finite Epochs
Jeff Z. HaoChen, Suvrit Sra
ICML, 2019 [PDF]