Haimeng Zhao

Haimeng Zhao

Undergraduate of Physics and Maths

Tsinghua University

Welcome!

Hello ~ I am Haimeng Zhao (赵海萌), an undergraduate of Physics and Mathematics at Zhili College, Tsinghua University. I’m deeply fascinated by how the universe works and how we can possibly understand it. So I started working in the intersection of Physics and Artificial Intelligence.

Specifically, my interest comes in two folds:

  • the foundation, application and interplay of quantum physics, information theory and statistics;
  • (quantum) machine learning for physics and physics for machine learning.

I’m currently an undergrad research fellow in John Preskill’s group at IQIM, Caltech. Before that I was an exchange student at EPFL, Switzerland, where I worked with Giuseppe Carleo and Filippo Vicentini on neural quantum states. In my sophomore year, I worked on AI for Astronomy with Wei Zhu at Tsinghua.

I am joining Caltech as a Physics graduate student in 2024 Fall!

Interests

  • Quantum Information, Statistics & Learning Theory
  • AI for Science, especially Physics & Astrophysics
  • Quantum Many-body Physics
  • Generative Learning

Education

  • Undergraduate, 2020 - 2024(expected)

    Physics, Tsinghua University

  • Outstanding Graduate, 2020

    Shanghai High School

Skills

Programming

High performance scientific computing with Python & C++.

Differentiable programming with JAX, PyTorch (6 years) & TensorFlow.

(Quantum) Machine Learning

(Quantum) Learning Theory,

Variational Quantum Algorithms,

Generaitive Learning,

Neural Differential Equations,

Computational Physics

(Quantum) Monte Carlo,

Tensor Network, DFT,

Neural Quantum State

Publications

(2024). Empirical Sample Complexity of Neural Network Mixed State Reconstruction. Quantum 8, 1358.

PDF Code

(2024). CPS Attack Detection under Limited Local Information in Cyber Security: A Multi-node Multi-class Classification Ensemble Approach. ACM Transactions on Sensor Networks 20 (2), 1-27.

PDF

(2023). Learning quantum states and unitaries of bounded gate complexity.

PDF

(2023). Non-IID Quantum Federated Learning with One-shot Communication Complexity. Quantum Machine Intelligence, 5(1), 3.

PDF Code Conf Talk

(2022). MAGIC: Microlensing Analysis Guided by Intelligent Computation. The Astronomical Journal, 164(5), 192.

PDF Code Conf Talk

Experience

 
 
 
 
 

AI for Quantum: Sample Complexity of Neural Quantum State Tomography

Advisor: Prof. Giuseppe Carleo & Filippo Vicentini, Computational Quantum Science Lab @ EPFL.

Aug 2022 – Jul 2023 First Author. Lausanne, Switzerland
Introduced control variates to control gradient variance and significantly reduce sample complexity. Conducted extensive numerical & theoretical studies to understand different sample complexity behavior. Benchmarked different tomography methods and propose to design quantum-resource-efficient NQSs.
 
 
 
 
 

Federated Learning in Multi-class Classification

In collaboration with Prof. Jingyi Zhang, Center for Statistical Science @ Tsinghua, and my friends Junyi & Yifu.

Apr 2022 – Apr 2022 Third Author. Beijing, China
Proved the key theorem in the paper, which enables one to merge partial classifiers trained in different nodes into a global one without leaking private data.
 
 
 
 
 

AI for Astro: ML Framework for Realistic Microlensing Event Analysis

Advisor: Prof. Wei Zhu, Department of Astronomy @ Tsinghua.

Oct 2021 – Jun 2022 First Author. Beijing, China
Introduced U-Net and neural controlled differential equations to parameter estimation of microlensing. Developed a machine learning framework for irregular astronomical time series, listed on NASA EMAC. Accelerate microlensing analysis by 5 orders of magnitude and successfully applied to real events for the first time.
 
 
 
 
 

Quantum AI: Non-IID Quantum Federated Learning

Single authored work. Extending Liu et al. to the quantum regime.

Jul 2021 – Sep 2022 Single Author. Beijing, China
Proposed and studied the non-IID quagmire in quantum federated learning, theoretically and numerically. Extended Liu et al. to a quantum algorithm. Conducted extensive numerics to show its robustness and efficiency.
 
 
 
 
 

AI for HEP-Ex: A Neutrino Data Analysis Tournament

Advisor: Prof. Benda Xu, Department of Engineering Physics @ Tsinghua.

Jan 2021 – Jun 2021 First Prize & Most Innovative Algorithm. Beijing, China
Led a team that developed a simulation & machine learning pipeline to promote neutrino energy detection precision, a key step towards understanding the neutrino mass ordering problem.
 
 
 
 
 

AI for Vision: Learned Lossy Image Compression

Advisor: the Internet. In collaboration with a friend Peiyuan back in high school.

Sep 2018 – Dec 2019 First Author. Shanghai, China
Introduced a pruning method originally used in neural architecture search to the field of lossy image compression. Achieved the state-of-the-art performance with much simpler training procedure.

Contact