Bowen Lei

Bowen Lei

Hello! I am a Ph.D. candidate in the Department of Statistics at Texas A&M University and honored to be advised by Bani K. Mallick. Before joining Texas A&M University, I obtained a bachelor’s degree in Statistics at Renmin University of China and also minored in Mathematics and Economic Statistics.

In summer 2022, I was a machine learnining researcher intern at Apple Video Engineering team working with Andrew Bai and Fang-Yu Lin, exploring image quality assessment & improvement and designing image denoising pipeline. In summer 2021, I was a research intern at JD.COM American Search team working with Yun Xiao and Xi Xiong, studying cold start problems in recommendation system. I also spent a wonderful spring (2019) as Algorithm Engineer Intern working with Taiyun Wei at Percent, researching on attention architecture in machine translation and natural language processing.

Other than my work, I am a big fan of basketball. I love Los Angeles Lakers and Golden State Warriors. I also like soccer and love Real Madrid CF and Manchester United F.C. In addition, I also enjoy workout and climbing.

Email / CV / Google Scholar / Github / LinkedIn

Research

I am interested in safe & efficient large generative model and probabilistic machine learning. My current research is investigating how to improve the safety & efficiency of Generative AI (Diffusion Models, ChatGPT, GPT-X) Systems to achieve Pareto optimality between computing resources, decision safety, and model performance for both general & personalized AI.

Large Generative Model: Image Editing, Augmented Language Model, and Intelligent Agent Autonomy
Safe Deep Learning: Alignment, Uncertainty Quantification, Robust Generalization, Adaptation
Efficient Training & Inference: Sparse Training, Pruning, Data Distillation, Algorithm-hardware Co-design
Domains: Computer Vision, Natural Language Processing, Recommendation Systems, Sciences

News

08/2023: Invited to serve as a PC member for AAAI'24.
07/2023: One paper about Reliable Data Distillation was accepted to ICCV'23!
06/2023: Feel free to check out our latest work on Augmented LLM ReWOO (GitHub)!
05/2023: One paper about Reliable Rare Category Analysis on Graphs was accepted to KDD'23!
05/2023: Happy to join Video Engineering team at Apple as a machine learning researcher intern.
04/2023: Invited to give a talk at Machine Learning and Natural Language Processing Community Colloquium.
04/2023: Invited to give a talk at Capital of Statistics Cloud Lecture.
03/2023: Two papers about Dynamic Training was accepted to DAC'23!
03/2023: Invited to serve as a reviewer for Journal of Data Science.
02/2023: One paper about Accelerate Data Distillation was accepted to CVPR'23 (highlight, top 10%)!
01/2023: One paper about Calibrated Rigged Lottery was accepted to ICLR'23!
01/2023: One paper about Efficient Informed Proposals for Discrete Distributions was accepted to AISTATS'23!
01/2023: One paper about Spiking Neural Network Training Acceleration was accepted to DCAA'23!
01/2023: Invited to serve as a reviewer for the DL-Hardware Co-Design for AI Acceleration at AAAI'23.
11/2022: Invited to give a talk at CSC 791&591: Advanced Topics in Efficient Deep Learning in NC State University.
10/2022: Presented a poster about Bayesian optimization at TRIPODS annual Data Science conference, 2022.
07/2022: Presented a poster about sparse training acceleration at SNN Workshop 2022.
05/2022: Happy to join Video Engineering team at Apple as a machine learning researcher intern.
02/2022: Invited to serve as a external conference reviewer for KDD'22.
02/2022: Invited to serve as a conference reviewer for ICML'22.
12/2021: One paper about Bayesian optimization was accepted to Nature Computational Materials!
05/2021: Happy to join Search team at JD.COM American as a research intern.
04/2021: Invited to give a talk at STAT 21019063: Data Science in Action in Renmin University of China.
07/2020: One paper about Bayesian learning in sciences was accepted to PloS one.

Work Experiences

Video Engineering team, Apple
ML Researcher Intern; Manager: Hui Chao; Maojing Fu (May -- Aug 2023)

Video Engineering team, Apple
ML Researcher Intern; Manager: Andrew Bai; Fang-Yu Lin (May -- Aug 2022)
Project: image quality assessment & improvement and image denoising pipeline.

Search team, JD.COM American.
Research Intern; Manager: Yun Xiao; Xi Xiong (May -- Jul 2021)
Project: cold start problems in recommendation system using cross-domain and group information.

Department of Data Modeling, Percent.
Algorithm Engineer Intern; Manager: Taiyun Wei (Feb -- Apr 2019)
Researched on attention architecture in machine translation and natural language processing.
Project: building machine translation system that can adapt to multiple domains and languages.

Publications

Calibrating the Rigged Lottery: Making All Tickets Reliable
Bowen Lei, Ruqi Zhang, Dongkuan Xu, Bani K. Mallick.
ICLR 2023 (PDF / Code)

Bayesian Optimization with Adaptive Surrogate Models for Automated Experimental Design
Bowen Lei, Tanner Quinn Kirk, Anirban Bhattacharya, Debdeep Pati,
Xiaoning Qian, Raymundo Arroyave, Bani K. Mallick.
Nature Computational Materials (PDF)

Accelerating dataset distillation via model augmentation
Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding,
Yao Li, Dongkuan Xu.
CVPR 2023 (PDF)

Rethinking Data Distillation: Do Not Overlook Calibration
Dongyao Zhu, Bowen Lei, Jie Zhang, Yanbo Fang, Yiqun Xie, Ruqi Zhang, Dongkuan Xu.
ICCV 2023 (to appear)

Towards Reliable Rare Category Analysis on Graphs via Individual Calibration
Longfeng Wu, Bowen Lei, Dongkuan Xu, Dawei Zhou.
KDD 2023 (to appear)

Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off
Shaoyi Huang, Bowen Lei, Dongkuan Xu, Hongwu Peng, Mimi Xie, Caiwen Ding.
DAC 2023 (PDF)

Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration
Shaoyi Huang, Haowen Fang, Kaleel Mahmood, Bowen Lei, Nuo Xu, Bin Lei, Yue Sun, Dongkuan Xu,
Wujie Wen and Caiwen Ding.
DAC 2023 (to appear)

Efficient Informed Proposals for Discrete Distributions via Newton’s Series Approximation
Yue Xiang, Dongyao Zhu, Bowen Lei, Dongkuan Xu, Ruqi Zhang.
AISTATS 2023 (PDF/ Code)

Estimation of COVID-19 spread curves integrating global data and borrowing information
Lee, Se Yoon, Bowen Lei, and Bani K. Mallick.
PloS one (PDF / Code)

Submitted Papers

Reliable and Efficient Out-of-distribution Detection
Bowen Lei, Dongkuan Xu, Ruqi Zhang, Bani K. Mallick.
Submitted in 2023 (to appear)

Accelerating and Stabilizing Sparse Training
Bowen Lei, Dongkuan Xu, Ruqi Zhang, Shuren He, Bani K. Mallick.
Submitted in 2023 (PDF)

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata Mukherjee, Yuchen Liu, Dongkuan Xu.
Submitted in 2023 (PDF)

Professional Services

Conference Reviewer:
- ICML'22
- KDD'22
- DCAA'23

Teaching Experiences

Teaching Assistant at Texas A&M University
- STAT 605 - Advanced Statistical Computation, Fall 2022
  Instructor: Prof. Pati
- STAT 641, Methods of Statistics, Spring 2022
  Instructor: Prof. Ghosh
- STAT 657, Advanced Programming Using SAS, Spring 2021
  Instructor: Prof. Kincheloe
- STAT 645, Applied Biostatistics, Fall 2020
  Instructor: Prof. Sinha

Talks

Test Accuracy is Not All You Need: Less Cost & More Reliability
Colloquium, Apr. 2023.
Machine Learning and Natural Language Processing Community.
Test Accuracy is Not All You Need: Less Cost & More Reliability
Cloud Lecture, Apr. 2023.
Capital of Statistics.
Efficient and Reliable Sparse Training
CSC 791&591: Advanced Topics in Efficient Deep Learning, Nov. 2022.
NC State University.
Machine Learning in COVID-19 and Epidemiology
STAT 21019063: Data Science in Action, Apr. 2021.
Renmin University of China.

Honors and Awards

Bachelor of Science (B.S.)
- First Prize, Student Scholarship for Excellent Academic Performance (top 2 ), 2017
- Grand Prize in the 19th "Innovation Cup" Academic Research Competition (top 1\%), 2017
- First Prize, University Extracurricular Academic and Technology Competition (top 0.1\%), 2017
- First Prize, Fei Xiaotong Scholarship for Excellent Academic Performance (top 2), 2016

Extracurricular Activities

Assistant editor of Capital of Statistics, 2017-Present
Member and editor of CluBear, 2017-2019
Organizer and volunteer of the China R Conference, 2017-2019
Statistical consultant of Visualization and Visual Analytics Group in Peking University, 2018
Minister of Young Volunteers Association of the Department of Statistics, 2016-2017

Misc

Basketball:
Travel:
Archery:

*Last updated on 10/31/2022*
This guy makes a nice webpage