본문 바로가기 주메뉴 바로가기
검색 검색영역닫기 검색 검색영역닫기 ENGLISH 메뉴 전체보기 메뉴 전체보기

학술행사

콜로퀴움

SDEs in Machine Learning

등록일자 : 2022-06-13

https://icim.nims.re.kr/post/event/924

  • 발표자  강완모(카이스트)
  • 기간  2022-06-23 ~ 2022-06-23
  • 장소  광교 산업수학혁신센터 세미나실
  • 주최  산업수학혁신센터

1. 일시: 2022년 6월 23일(목), 14:00-16:00

2. 장소: 광교 테크노밸리 산업수학혁신센터 세미나실

3. 발표자: 강완모 (카이트스)

4. 주요내용: SDEs in Machine Learning

There have been various applications of stochastic differential equation (SDE) theories in machine learning research. In this talk, we review how SDE helps to understand the stochastic behaviors of SGD. In addition to being a tool in the analysis of ML algorithms, SDE itself became a part of algorithms in generative modeling recently. We will briefly review the score-based diffusion models and discuss a new result of 'Soft Truncation'. This talk is based on a work with Dongjun Kim and Il-Chul Moon.

현장강의만 진행합니다

1. 일시: 2022년 6월 23일(목), 14:00-16:00

2. 장소: 광교 테크노밸리 산업수학혁신센터 세미나실

3. 발표자: 강완모 (카이트스)

4. 주요내용: SDEs in Machine Learning

There have been various applications of stochastic differential equation (SDE) theories in machine learning research. In this talk, we review how SDE helps to understand the stochastic behaviors of SGD. In addition to being a tool in the analysis of ML algorithms, SDE itself became a part of algorithms in generative modeling recently. We will briefly review the score-based diffusion models and discuss a new result of 'Soft Truncation'. This talk is based on a work with Dongjun Kim and Il-Chul Moon.

현장강의만 진행합니다

이 페이지에서 제공하는 정보에 대해 만족하십니까?