1 code implementation • 19 Feb 2024 • Uijeong Jang, Jason D. Lee, Ernest K. Ryu
Low-rank adaptation (LoRA) has become the standard approach for parameter-efficient fine-tuning of large language models (LLM), but our theoretical understanding of LoRA has been limited.
1 code implementation • 27 Oct 2023 • Sehyun Kwon, Jaeseung Park, Minkyu Kim, Jaewoong Cho, Ernest K. Ryu, Kangwook Lee
Classical clustering methods do not provide users with direct control of the clustering results, and the clustering results may not be consistent with the relevant criterion that a user has in mind.
1 code implementation • 27 Apr 2023 • Sehyun Kwon, Joo Young Choi, Ernest K. Ryu
In many computer vision applications, images are acquired with arbitrary or random rotations and translations, and in such setups, it is desirable to obtain semantic representations disentangled from the image orientation.
1 code implementation • 24 Feb 2022 • Taeho Yoon, Youngsuk Park, Ernest K. Ryu, Yuyang Wang
Probabilistic time series forecasting has played critical role in decision-making processes due to its capability to quantify uncertainties.
1 code implementation • 7 Feb 2022 • Jongmin Lee, Joo Young Choi, Ernest K. Ryu, Albert No
The tremendous recent progress in analyzing the training dynamics of overparameterized neural networks has primarily focused on wide networks and therefore does not sufficiently address the role of depth in deep learning.
1 code implementation • 15 Feb 2021 • Albert No, Taeho Yoon, Sehyun Kwon, Ernest K. Ryu
Generative adversarial networks (GAN) are a widely used class of deep generative models, but their minimax training dynamics are not understood very well.
no code implementations • 25 Sep 2019 • Ernest K. Ryu, Kun Yuan, Wotao Yin
Despite remarkable empirical success, the training dynamics of generative adversarial networks (GAN), which involves solving a minimax game using stochastic gradients, is still poorly understood.
no code implementations • 26 May 2019 • Ernest K. Ryu, Kun Yuan, Wotao Yin
Despite remarkable empirical success, the training dynamics of generative adversarial networks (GAN), which involves solving a minimax game using stochastic gradients, is still poorly understood.
1 code implementation • 14 May 2019 • Ernest K. Ryu, Jialin Liu, Sicheng Wang, Xiaohan Chen, Zhangyang Wang, Wotao Yin
Plug-and-play (PnP) is a non-convex framework that integrates modern denoising priors, such as BM3D or deep learning-based denoisers, into ADMM or other proximal algorithms.
1 code implementation • 1 Dec 2018 • Ernest K. Ryu, Adrien B. Taylor, Carolina Bergeling, Pontus Giselsson
We propose a methodology for studying the performance of common splitting methods through semidefinite programming.
Optimization and Control 47H05 47H09 68Q25 90C22 90C25 90C30 90C60
1 code implementation • 31 Oct 2018 • Ernest K. Ryu, Seyoon Ko, Joong-Ho Won
Many imaging problems, such as total variation reconstruction of X-ray computed tomography (CT) and positron-emission tomography (PET), are solved via a convex optimization problem with near-circulant, but not actually circulant, linear systems.
Optimization and Control