FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2396019715> ?p ?o ?g. }

• W2396019715 abstract "Matrix completion is a basic machine learning problem that has wide applications, especially in collaborative filtering and recommender systems. Simple non-convex optimization algorithms are popular and effective in practice. Despite recent progress in proving various non-convex algorithms converge from a good initial point, it remains unclear why random or arbitrary initialization suffices in practice. We prove that the commonly used non-convex objective function for textit{positive semidefinite} matrix completion has no spurious local minima --- all local minima must also be global. Therefore, many popular optimization algorithms such as (stochastic) gradient descent can provably solve positive semidefinite matrix completion with textit{arbitrary} initialization in polynomial time. The result can be generalized to the setting when the observed entries contain noise. We believe that our main proof strategy can be useful for understanding geometric properties of other statistical problems involving partial or noisy observations." @default.
• W2396019715 created "2016-06-24" @default.
• W2396019715 creator A5035001911 @default.
• W2396019715 creator A5059740024 @default.
• W2396019715 creator A5061905935 @default.
• W2396019715 date "2016-05-24" @default.
• W2396019715 modified "2023-09-27" @default.
• W2396019715 title "Matrix Completion has No Spurious Local Minimum" @default.
• W2396019715 cites W1492459858 @default.
• W2396019715 cites W1884015253 @default.
• W2396019715 cites W1884359871 @default.
• W2396019715 cites W1976618413 @default.
• W2396019715 cites W2009941369 @default.
• W2396019715 cites W2015836240 @default.
• W2396019715 cites W2052044664 @default.
• W2396019715 cites W2078626246 @default.
• W2396019715 cites W2110451175 @default.
• W2396019715 cites W2111297856 @default.
• W2396019715 cites W2116680824 @default.
• W2396019715 cites W2120872934 @default.
• W2396019715 cites W2122090912 @default.
• W2396019715 cites W2134332047 @default.
• W2396019715 cites W2134618502 @default.
• W2396019715 cites W2143075842 @default.
• W2396019715 cites W2145962650 @default.
• W2396019715 cites W2146130798 @default.
• W2396019715 cites W2189224591 @default.
• W2396019715 cites W2268788034 @default.
• W2396019715 cites W2279984491 @default.
• W2396019715 cites W2283214199 @default.
• W2396019715 cites W2399402693 @default.
• W2396019715 cites W2611328865 @default.
• W2396019715 cites W2616032753 @default.
• W2396019715 cites W2616050959 @default.
• W2396019715 cites W2963684688 @default.
• W2396019715 cites W2963972677 @default.
• W2396019715 cites W2964106499 @default.
• W2396019715 cites W2964346891 @default.
• W2396019715 cites W1962325108 @default.
• W2396019715 cites W2144730813 @default.
• W2396019715 hasPublicationYear "2016" @default.
• W2396019715 type Work @default.
• W2396019715 sameAs 2396019715 @default.
• W2396019715 citedByCount "152" @default.
• W2396019715 countsByYear W23960197152015 @default.
• W2396019715 countsByYear W23960197152016 @default.
• W2396019715 countsByYear W23960197152017 @default.
• W2396019715 countsByYear W23960197152018 @default.
• W2396019715 countsByYear W23960197152019 @default.
• W2396019715 countsByYear W23960197152020 @default.
• W2396019715 countsByYear W23960197152021 @default.
• W2396019715 crossrefType "posted-content" @default.
• W2396019715 hasAuthorship W2396019715A5035001911 @default.
• W2396019715 hasAuthorship W2396019715A5059740024 @default.
• W2396019715 hasAuthorship W2396019715A5061905935 @default.
• W2396019715 hasConcept C101901036 @default.
• W2396019715 hasConcept C106487976 @default.
• W2396019715 hasConcept C111472728 @default.
• W2396019715 hasConcept C112680207 @default.
• W2396019715 hasConcept C11413529 @default.
• W2396019715 hasConcept C114466953 @default.
• W2396019715 hasConcept C119857082 @default.
• W2396019715 hasConcept C121332964 @default.
• W2396019715 hasConcept C126255220 @default.
• W2396019715 hasConcept C134306372 @default.
• W2396019715 hasConcept C138885662 @default.
• W2396019715 hasConcept C145446738 @default.
• W2396019715 hasConcept C153258448 @default.
• W2396019715 hasConcept C154945302 @default.
• W2396019715 hasConcept C157972887 @default.
• W2396019715 hasConcept C159985019 @default.
• W2396019715 hasConcept C163716315 @default.
• W2396019715 hasConcept C186633575 @default.
• W2396019715 hasConcept C192562407 @default.
• W2396019715 hasConcept C199360897 @default.
• W2396019715 hasConcept C2524010 @default.
• W2396019715 hasConcept C2778459887 @default.
• W2396019715 hasConcept C2780586882 @default.
• W2396019715 hasConcept C33923547 @default.
• W2396019715 hasConcept C41008148 @default.
• W2396019715 hasConcept C50644808 @default.
• W2396019715 hasConcept C62520636 @default.
• W2396019715 hasConcept C97256817 @default.
• W2396019715 hasConceptScore W2396019715C101901036 @default.
• W2396019715 hasConceptScore W2396019715C106487976 @default.
• W2396019715 hasConceptScore W2396019715C111472728 @default.
• W2396019715 hasConceptScore W2396019715C112680207 @default.
• W2396019715 hasConceptScore W2396019715C11413529 @default.
• W2396019715 hasConceptScore W2396019715C114466953 @default.
• W2396019715 hasConceptScore W2396019715C119857082 @default.
• W2396019715 hasConceptScore W2396019715C121332964 @default.
• W2396019715 hasConceptScore W2396019715C126255220 @default.
• W2396019715 hasConceptScore W2396019715C134306372 @default.
• W2396019715 hasConceptScore W2396019715C138885662 @default.
• W2396019715 hasConceptScore W2396019715C145446738 @default.
• W2396019715 hasConceptScore W2396019715C153258448 @default.
• W2396019715 hasConceptScore W2396019715C154945302 @default.
• W2396019715 hasConceptScore W2396019715C157972887 @default.
• W2396019715 hasConceptScore W2396019715C159985019 @default.
• W2396019715 hasConceptScore W2396019715C163716315 @default.

• next