학술행사
- 발표자 채민우 교수(포항공과대학교)
- 개최일시 2023-06-08 13:00-15:00
-
일시: 2023년 6월 8일(목), 13:00-15:00
-
장소: 판교 테크노밸리 산업수학혁신센터 세미나실
- 경기 성남시 수정구 대왕판교로 815, 기업지원허브 231호 국가수리과학연구소
- 무료주차는 2시간 지원됩니다.
-
발표자: 채민우 교수(포항공과대학교)
-
주요내용: Statistical perspective of deep generative models
In the first part of this talk, we will provide a brief introduction to deep generative models, such as the variational autoencoder (VAE), generative adversarial networks (GAN), normalizing flows, and score-based methods, from a statistician's viewpoint. In the second part, we will focus on statistical theory for deep generative models, with an emphasis on VAE and GAN type estimators. Both VAE and GAN estimators achieve the minimax optimal rate in a classical nonparametric density estimation framework. Additionally, we will consider a structured distribution estimation where the target distribution is concentrated around a low-dimensional structure, allowing for singularity to the Lebesgue measure. The convergence rates of both estimators depend solely on the structure of the true distribution and the noise level. Moreover, GAN achieves a faster convergence rate than VAE. Finally, we will discuss the minimax optimal rate of the structured distribution estimation under consideration.
*현장 강의만 진행예정입니다.
-
일시: 2023년 6월 8일(목), 13:00-15:00
-
장소: 판교 테크노밸리 산업수학혁신센터 세미나실
- 경기 성남시 수정구 대왕판교로 815, 기업지원허브 231호 국가수리과학연구소
- 무료주차는 2시간 지원됩니다.
-
발표자: 채민우 교수(포항공과대학교)
-
주요내용: Statistical perspective of deep generative models
In the first part of this talk, we will provide a brief introduction to deep generative models, such as the variational autoencoder (VAE), generative adversarial networks (GAN), normalizing flows, and score-based methods, from a statistician's viewpoint. In the second part, we will focus on statistical theory for deep generative models, with an emphasis on VAE and GAN type estimators. Both VAE and GAN estimators achieve the minimax optimal rate in a classical nonparametric density estimation framework. Additionally, we will consider a structured distribution estimation where the target distribution is concentrated around a low-dimensional structure, allowing for singularity to the Lebesgue measure. The convergence rates of both estimators depend solely on the structure of the true distribution and the noise level. Moreover, GAN achieves a faster convergence rate than VAE. Finally, we will discuss the minimax optimal rate of the structured distribution estimation under consideration.
*현장 강의만 진행예정입니다.
