Lee Optimization Group

We pursue research in machine learning and optimization. To this end, we develop theories and algorithms using computational and mathematical tools. Our ultimate goal is to provide robust and provable solutions to challenging problems in artificial intelligence, particularly those in large-scale settings. We are passionate about translating our findings into practical applications that can benefit society.

Research focus

Optimization for Model Compression   As modern AI models, particularly deep neural networks, grow increasingly large and computationally demanding, model compression has become essential for enabling broader and more sustainable use of AI technologies. We develop optimization methods to compress large models so that they can run more efficiently at training and inference without significantly compromising their performance.

Optimization for Deep Learning   Optimization has been central to the success of deep learning, yet there remain many challenges to address such as non-convexity, high dimensionality, and scalability. We study both theoretical foundations—such as convergence guarantees and generalization properties—and practical algorithms, including stochastic, adaptive, and second-order methods, so as to come up with efficient and principled optimization methods.

Optimization for Collaborative Learning   Collaborative machine learning is a promising learning paradigm that allows participants to work together to train a model without necessarily sharing their raw data. However, frequent exchange of updates can overwhelm networks, especially with large models or slow connections. We address such a unique set of challenges due to its distributed and often decentralized nature by developing efficient and scalable solutions.

Optimization for Other Applications   Optimization is a versatile tool that can be applied to a wide range of machine learning applications. We are currently focused on addressing challenges surrounding large language models, particularly those involving learning in black-box environments, continual adaptation, and multi-modal contexts.

Members

Administrator

Dami So

Graduate students

Jinseok Chung   🏃 dual based optimization

Donghyun Oh   🏀 parameter-free optimization

Sungbin Shin   🎧 model optimization

Dahun Shin   🎬 second-order optimization

Dongyeop Lee   🎹 dual based optimization

Seonghwan Park   🎙 zeroth-order optimization

Jueun Mun   🥊 decentralized optimization

Jaehyeon Jeong   🚴 parameter-free optimization

Jihun Kim   🏸 decentralized optimization

Yongjun Kim   🏋 zeroth-order optimization

Kwanhee Lee   🎸 model optimization

Hyunji Jung   🎤 optimization theory

Minkyoung Song   🎶 applied optimization

Hyeondo Jang   🏋 model optimization

Stories

We also spend time together on various occasions (see gallery for more).

Join us

We are always on the lookout for talented and motivated students to join us!

Interns   We are actively hiring intern students. Please see this list of student projects.

MS/PhD   We have a few open positions for graduate students for the upcoming terms.

ALL   Please feel free to reach out if you have any questions about us. Otherwise, we suggest you consider applying for a position by filling this application form.

Acknowledgements

Our research is generously supported by multiple organizations including government agencies (NRF, IITP), industry (Google, Samsung, Naver, Intel), and academic institutions (POSTECH, Yonsei).