DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 윤철희 | - |
dc.contributor.author | Cha, Jaeyoung | - |
dc.contributor.author | 차재영 | - |
dc.date.accessioned | 2024-07-30T19:30:42Z | - |
dc.date.available | 2024-07-30T19:30:42Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096079&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321374 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2024.2,[iv, 45 p. :] | - |
dc.description.abstract | We study convergence lower bounds of without-replacement stochastic gradient descent (SGD) for solving smooth (strongly-)convex finite-sum minimization problems. Unlike most existing results focusing on lower bounds for SGD with Random Reshuffling where the random permutation is chosen independently on each epoch to sample the component function in each iterate, we seek bounds applicable to arbitrary permutation-based SGD. This method includes all variants that carefully select the best permutation beyond Random Reshuffling. Notably, our bounds significantly improve upon existing lower bounds and tightly match the upper bounds shown for a recently proposed algorithm called GraB, across all factors including the number of component functions $n$, the number of epochs $K$, and the condition number $\kappa$. We also extend our bounds to arbitrary weighted average iterates, providing a generalized result that covers the final iterate. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 확률적 경사 하강법▼a수렴 속도 하한▼a비복원 추출 | - |
dc.subject | Stochastic gradient descent▼aConvergence lower bound▼aWithout-replacement | - |
dc.title | Optimal convergence rate of without-replacement SGD | - |
dc.title.alternative | 비복원 추출 기반 확률적 경사 하강법의 최적 수렴 속도 분석 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Yun, Chulhee | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.