Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014145244> ?p ?o ?g. }
- W3014145244 abstract "Many statistical learning problems have recently been shown to be amenable to Semi-Definite Programming (SDP), with community detection and clustering in Gaussian mixture models as the most striking instances [javanmard et al., 2016]. Given the growing range of applications of SDP-based techniques to machine learning problems, and the rapid progress in the design of efficient algorithms for solving SDPs, an intriguing question is to understand how the recent advances from empirical process theory can be put to work in order to provide a precise statistical analysis of SDP estimators. In the present paper, we borrow cutting edge techniques and concepts from the learning theory literature, such as fixed point equations and excess risk curvature arguments, which yield general estimation and prediction results for a wide class of SDP estimators. From this perspective, we revisit some classical results in community detection from [guedon et al.,2016] and [chen et al., 2016], and we obtain statistical guarantees for SDP estimators used in signed clustering, group synchronization and MAXCUT." @default.
- W3014145244 created "2020-04-10" @default.
- W3014145244 creator A5028263110 @default.
- W3014145244 creator A5039600886 @default.
- W3014145244 creator A5051445130 @default.
- W3014145244 creator A5059835438 @default.
- W3014145244 date "2020-04-04" @default.
- W3014145244 modified "2023-10-18" @default.
- W3014145244 title "Learning with Semi-Definite Programming: new statistical bounds based on fixed point analysis and excess risk curvature" @default.
- W3014145244 cites W108936587 @default.
- W3014145244 cites W1529624360 @default.
- W3014145244 cites W1537662695 @default.
- W3014145244 cites W1584951881 @default.
- W3014145244 cites W1651008648 @default.
- W3014145244 cites W1803708361 @default.
- W3014145244 cites W1825447146 @default.
- W3014145244 cites W1894414046 @default.
- W3014145244 cites W1926890729 @default.
- W3014145244 cites W1964150977 @default.
- W3014145244 cites W1965656937 @default.
- W3014145244 cites W1968398095 @default.
- W3014145244 cites W1969705577 @default.
- W3014145244 cites W1970377488 @default.
- W3014145244 cites W1974967023 @default.
- W3014145244 cites W198244778 @default.
- W3014145244 cites W1985123706 @default.
- W3014145244 cites W1986219860 @default.
- W3014145244 cites W1988874269 @default.
- W3014145244 cites W2003672952 @default.
- W3014145244 cites W2007104311 @default.
- W3014145244 cites W2010353172 @default.
- W3014145244 cites W2014793162 @default.
- W3014145244 cites W2015953751 @default.
- W3014145244 cites W2026287238 @default.
- W3014145244 cites W2033957915 @default.
- W3014145244 cites W2043919728 @default.
- W3014145244 cites W2047940964 @default.
- W3014145244 cites W2049371785 @default.
- W3014145244 cites W2049393399 @default.
- W3014145244 cites W2060783161 @default.
- W3014145244 cites W2065939443 @default.
- W3014145244 cites W2066215526 @default.
- W3014145244 cites W2069816168 @default.
- W3014145244 cites W2072951627 @default.
- W3014145244 cites W2073415627 @default.
- W3014145244 cites W2078289947 @default.
- W3014145244 cites W2079155241 @default.
- W3014145244 cites W2083412275 @default.
- W3014145244 cites W2085427851 @default.
- W3014145244 cites W2088911135 @default.
- W3014145244 cites W2094508696 @default.
- W3014145244 cites W2104876468 @default.
- W3014145244 cites W2135762244 @default.
- W3014145244 cites W2138505091 @default.
- W3014145244 cites W2141380252 @default.
- W3014145244 cites W2142517301 @default.
- W3014145244 cites W2143703915 @default.
- W3014145244 cites W2145080587 @default.
- W3014145244 cites W2147554450 @default.
- W3014145244 cites W2155434899 @default.
- W3014145244 cites W2156894402 @default.
- W3014145244 cites W2167623372 @default.
- W3014145244 cites W2174754147 @default.
- W3014145244 cites W2234995292 @default.
- W3014145244 cites W2268674159 @default.
- W3014145244 cites W2506488269 @default.
- W3014145244 cites W2522078129 @default.
- W3014145244 cites W2567866584 @default.
- W3014145244 cites W2567976503 @default.
- W3014145244 cites W2787248994 @default.
- W3014145244 cites W2884993474 @default.
- W3014145244 cites W2891159302 @default.
- W3014145244 cites W2894988545 @default.
- W3014145244 cites W2922291765 @default.
- W3014145244 cites W2962699510 @default.
- W3014145244 cites W2963105348 @default.
- W3014145244 cites W2963264680 @default.
- W3014145244 cites W2963709905 @default.
- W3014145244 cites W2963860509 @default.
- W3014145244 cites W2963929357 @default.
- W3014145244 cites W2963957678 @default.
- W3014145244 cites W2964081830 @default.
- W3014145244 cites W2964176492 @default.
- W3014145244 cites W3013494708 @default.
- W3014145244 cites W3013880646 @default.
- W3014145244 cites W3105849782 @default.
- W3014145244 cites W3123255541 @default.
- W3014145244 cites W3187217851 @default.
- W3014145244 cites W3190120408 @default.
- W3014145244 cites W3210839039 @default.
- W3014145244 cites W404764422 @default.
- W3014145244 cites W568673721 @default.
- W3014145244 cites W572922989 @default.
- W3014145244 cites W608582638 @default.
- W3014145244 cites W653291882 @default.
- W3014145244 hasPublicationYear "2020" @default.
- W3014145244 type Work @default.
- W3014145244 sameAs 3014145244 @default.
- W3014145244 citedByCount "0" @default.
- W3014145244 crossrefType "posted-content" @default.