Matches in SemOpenAlex for { <https://semopenalex.org/work/W2078206853> ?p ?o ?g. }
- W2078206853 abstract "Given a dictionary of $M_n$ initial estimates of the unknown true regression function, we aim to construct linearly aggregated estimators that target the best performance among all the linear combinations under a sparse $q$-norm ($0 leq q leq 1$) constraint on the linear coefficients. Besides identifying the optimal rates of aggregation for these $ell_q$-aggregation problems, our multi-directional (or universal) aggregation strategies by model mixing or model selection achieve the optimal rates simultaneously over the full range of $0leq q leq 1$ for general $M_n$ and upper bound $t_n$ of the $q$-norm. Both random and fixed designs, with known or unknown error variance, are handled, and the $ell_q$-aggregations examined in this work cover major types of aggregation problems previously studied in the literature. Consequences on minimax-rate adaptive regression under $ell_q$-constrained true coefficients ($0 leq q leq 1$) are also provided. Our results show that the minimax rate of $ell_q$-aggregation ($0 leq q leq 1$) is basically determined by an effective model size, which is a sparsity index that depends on $q$, $t_n$, $M_n$, and the sample size $n$ in an easily interpretable way based on a classical model selection theory that deals with a large number of models. In addition, in the fixed design case, the model selection approach is seen to yield optimal rates of convergence not only in expectation but also with exponential decay of deviation probability. In contrast, the model mixing approach can have leading constant one in front of the target risk in the oracle inequality while not offering optimality in deviation probability." @default.
- W2078206853 created "2016-06-24" @default.
- W2078206853 creator A5015458882 @default.
- W2078206853 creator A5046540286 @default.
- W2078206853 creator A5048701309 @default.
- W2078206853 creator A5058391979 @default.
- W2078206853 date "2011-08-09" @default.
- W2078206853 modified "2023-10-16" @default.
- W2078206853 title "Adaptive Minimax Estimation over Sparse $ell_q$-Hulls" @default.
- W2078206853 cites W138682821 @default.
- W2078206853 cites W1484867920 @default.
- W2078206853 cites W1509060282 @default.
- W2078206853 cites W1521975636 @default.
- W2078206853 cites W1524622012 @default.
- W2078206853 cites W1547983335 @default.
- W2078206853 cites W1575244755 @default.
- W2078206853 cites W1615842772 @default.
- W2078206853 cites W1763273296 @default.
- W2078206853 cites W1963922536 @default.
- W2078206853 cites W1972968086 @default.
- W2078206853 cites W1973631422 @default.
- W2078206853 cites W1986931325 @default.
- W2078206853 cites W1989780425 @default.
- W2078206853 cites W1995771589 @default.
- W2078206853 cites W1996268356 @default.
- W2078206853 cites W2005838333 @default.
- W2078206853 cites W2009247956 @default.
- W2078206853 cites W2011283296 @default.
- W2078206853 cites W2021136548 @default.
- W2078206853 cites W2027223319 @default.
- W2078206853 cites W2035106560 @default.
- W2078206853 cites W2043471714 @default.
- W2078206853 cites W2046031028 @default.
- W2078206853 cites W2049637349 @default.
- W2078206853 cites W2050159069 @default.
- W2078206853 cites W2050880896 @default.
- W2078206853 cites W2056481711 @default.
- W2078206853 cites W2061317273 @default.
- W2078206853 cites W2062772460 @default.
- W2078206853 cites W2071168995 @default.
- W2078206853 cites W2071883464 @default.
- W2078206853 cites W2073123088 @default.
- W2078206853 cites W2083134779 @default.
- W2078206853 cites W2086403511 @default.
- W2078206853 cites W2086874647 @default.
- W2078206853 cites W2089752146 @default.
- W2078206853 cites W2095734615 @default.
- W2078206853 cites W2103215959 @default.
- W2078206853 cites W2105516453 @default.
- W2078206853 cites W2112172616 @default.
- W2078206853 cites W2116278188 @default.
- W2078206853 cites W2127300249 @default.
- W2078206853 cites W2129962685 @default.
- W2078206853 cites W2135046866 @default.
- W2078206853 cites W2156218552 @default.
- W2078206853 cites W2159700154 @default.
- W2078206853 cites W2166116275 @default.
- W2078206853 cites W2166956514 @default.
- W2078206853 cites W2168781258 @default.
- W2078206853 cites W2179504854 @default.
- W2078206853 cites W2295765951 @default.
- W2078206853 cites W2296616510 @default.
- W2078206853 cites W2340685325 @default.
- W2078206853 cites W2575082648 @default.
- W2078206853 cites W2964061037 @default.
- W2078206853 cites W2964097857 @default.
- W2078206853 cites W3099674110 @default.
- W2078206853 cites W3102942031 @default.
- W2078206853 cites W3104148512 @default.
- W2078206853 cites W3106224380 @default.
- W2078206853 doi "https://doi.org/10.48550/arxiv.1108.1961" @default.
- W2078206853 hasPublicationYear "2011" @default.
- W2078206853 type Work @default.
- W2078206853 sameAs 2078206853 @default.
- W2078206853 citedByCount "5" @default.
- W2078206853 countsByYear W20782068532013 @default.
- W2078206853 countsByYear W20782068532014 @default.
- W2078206853 countsByYear W20782068532023 @default.
- W2078206853 crossrefType "posted-content" @default.
- W2078206853 hasAuthorship W2078206853A5015458882 @default.
- W2078206853 hasAuthorship W2078206853A5046540286 @default.
- W2078206853 hasAuthorship W2078206853A5048701309 @default.
- W2078206853 hasAuthorship W2078206853A5058391979 @default.
- W2078206853 hasBestOaLocation W20782068531 @default.
- W2078206853 hasConcept C105795698 @default.
- W2078206853 hasConcept C114614502 @default.
- W2078206853 hasConcept C126255220 @default.
- W2078206853 hasConcept C127162648 @default.
- W2078206853 hasConcept C134306372 @default.
- W2078206853 hasConcept C149728462 @default.
- W2078206853 hasConcept C17744445 @default.
- W2078206853 hasConcept C185429906 @default.
- W2078206853 hasConcept C191795146 @default.
- W2078206853 hasConcept C199539241 @default.
- W2078206853 hasConcept C28826006 @default.
- W2078206853 hasConcept C31258907 @default.
- W2078206853 hasConcept C33923547 @default.
- W2078206853 hasConcept C41008148 @default.
- W2078206853 hasConcept C48921125 @default.
- W2078206853 hasConcept C57869625 @default.