Mendeley出力
＜会議発表資料＞
SPLITTING ALGORITHMS FOR NONCONVEX OPTIMIZATION: UNIFIED ANALYSIS AND NEWTON-TYPE ACCELERATION
| 作成者 | |
|---|---|
| 本文言語 | |
| 発行日 | |
| 会議情報 | |
| アクセス権 | |
| 概要 | We provide a unified interpretation of splitting algorithms for nonconvex optimization through the lens of majorization-minimization. Possibly under assumptions to compensate the lack of convexity, th...is setting is general enough to cover ADMM as well as forward-backward, Douglas-Rachford and Davis-Yin splittings. Proximal envelopes, a generalization of the Moreau envelope, are shown to be natural merit functions for establishing convergence results. Their regularity properties also enable the integration of fast direction of quasi-Newton-type, that differently from any other approach for nonsmooth optimization preserve the same operation complexity of the original splitting scheme.続きを見る |
| 目次 | Introduction Convex splitting algorithms Nonconvexity? Goals Algorithmic design The majorization-minimization principle Generalized proximal MM algorithms A unified convergence analysis Envelope functions Notable examples DRS ADMM DYS (Proximal ADMM) (Chambolle-Pock) “Acceleration” Challenges of higher-order methods The Continuous-Lyapunov Descent framework Simulations Conclusions続きを見る |
詳細
| レコードID | |
|---|---|
| 登録日 | 2023.06.16 |
| 更新日 | 2023.06.16 |