학과 세미나 및 콜로퀴엄

구분 SAARC 세미나
분류 SAARC 세미나
제목 Shuffling-based stochastic optimization methods: bridging the theory-practice gap
Abstract Stochastic finite-sum optimization problems are ubiquitous in many areas such as machine learning, and stochastic optimization algorithms to solve these finite-sum problems are actively studied in the literature. However, there is a major gap between practice and theory: practical algorithms shuffle and iterate through component indices, while most theoretical analyses of these algorithms assume uniformly sampling the indices. In this talk, we talk about recent research efforts to close this theory-practice gap. We will discuss recent developments in the theoretical convergence analysis of shuffling-based optimization methods. We will first consider minimization algorithms, mainly focusing on stochastic gradient descent (SGD) with shuffling; we will then briefly talk about some new progress on minimax optimization methods.
일시 2022-11-11 (Fri) / 10:00 ~ 11:00 ** 날짜에 유의하세요. **
장소 Zoom (ID: 683 181 3833 / PW: saarc)
강연언어 한국어 (필요한 경우 영어 가능) ( )
강연자성명 윤철희
강연자소속 KAIST 김재철 AI 대학원
강연자홈페이지
기타정보
초청인 확률 해석 및 응용 연구센터
URL https://us06web.zoom.us/j/6831813833?pwd=VUhUbmY3d0pKemt6ZlhSWU9jQ3d1QT09
담당자 확률 해석 및 응용 연구센터
연락처 042-350-8111/8117