Assistant Professor
City University of Hong Kong (CityU)
luzhichaocn [at] gmail [dot] com

Zhichao Lu received Ph.D degree in Electrical and Computer Engineering from Michigan State University under the supervision of Prof. Kalyanmoy Deb (FIEEE, FACM), where he studied bilevel optimization, evolutionary multi-objective optimization, and neural architecture search.

In the broad context of AI, his current research focuses on the intersections of evolutionary computation, learning, and optimization, notably on developing efficient and automated ML/DL algorithms and systems, with the overarching goal of making AI accessible to everyone.

Prospective Students: I am always looking for self-motivated students with strong mathematical and programming background. Please refer to openings for potential opportunities.
Recent News
Selected Research
Neural architecture search as multiobjective optimization benchmarks: Problem formulation and performance assessment
Zhichao Lu , Ran Cheng, Yaochu Jin, Kay Chen Tan, Kalyanmoy Deb
IEEE TEVC, 2023  
arXiv / slides / code

Transforming Neural Architecture Search (NAS) into multiobjective optimization problems. A benchmark suite for testing evolutionary algorithms in deep learning.

Revisiting Residual Networks for Adversarial Robustness
Shihua Huang, Zhichao Lu , Kalyanmoy Deb, Vishnu N. Boddeti
CVPR, 2023  
arXiv / poster / code

A holistic study on the impact of architectural design on adversarial robustness, showing that architecture contributes as much as, if not more than, adversarial training to adversarial robustness.

Neural Architecture Transfer
Zhichao Lu , Gautam Sreekumar, Erik Goodman, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu N. Boddeti
IEEE TPAMI, 2021  
arXiv / video / code

Improve practical utilities of neural architecture search through many-objective optimization, iterative surrogate modeling, and transfer learning.

NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search
Zhichao Lu , Kalyanmoy Deb, Erik Goodman, Wolfgang Banzhaf, Vishnu N. Boddeti
ECCV, 2020   (Oral Presentation)
arXiv / video / code

An efficient multi-objective neural architecture search framework. It can be easily integrated with most of search spaces.

NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
Zhichao Lu , Ian Whalen, Vishnu N. Boddeti, Yashesh Dhebar, Kalyanmoy Deb, Erik Goodman, Wolfgang Banzhaf
GECCO, 2019   (Oral Presentation, Best Paper Award)
arXiv / video / code / extended abstract (invited by IJCAI '20)

An evolutionary multi-objective search algorithm for evolving DNN architectures automatically.