FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897313170> ?p ?o ?g. }

• W2897313170 abstract "Nonlinear kernels can be approximated using finite-dimensional feature maps for efficient risk minimization. Due to the inherent trade-off between the dimension of the (mapped) feature space and the approximation accuracy, the key problem is to identify promising (explicit) features leading to a satisfactory out-of-sample performance. In this work, we tackle this problem by efficiently choosing such features from multiple kernels in a greedy fashion. Our method sequentially selects these explicit features from a set of candidate features using a correlation metric. We establish an out-of-sample error bound capturing the trade-off between the error in terms of explicit features (approximation error) and the error due to spectral properties of the best model in the Hilbert space associated to the combined kernel (spectral error). The result verifies that when the (best) underlying data model is sparse enough, i.e., the spectral error is negligible, one can control the test error with a small number of explicit features, that can scale poly-logarithmically with data. Our empirical results show that given a fixed number of explicit features, the method can achieve a lower test error with a smaller time cost, compared to the state-of-the-art in data-dependent random features." @default.
• W2897313170 created "2018-10-26" @default.
• W2897313170 creator A5020766546 @default.
• W2897313170 creator A5040922600 @default.
• W2897313170 date "2018-10-09" @default.
• W2897313170 modified "2023-09-27" @default.
• W2897313170 title "Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels" @default.
• W2897313170 cites W1489867037 @default.
• W2897313170 cites W1518544712 @default.
• W2897313170 cites W1518932425 @default.
• W2897313170 cites W1551209770 @default.
• W2897313170 cites W1814624729 @default.
• W2897313170 cites W1920328734 @default.
• W2897313170 cites W1949476142 @default.
• W2897313170 cites W1989009613 @default.
• W2897313170 cites W1994520254 @default.
• W2897313170 cites W2065321782 @default.
• W2897313170 cites W2091886411 @default.
• W2897313170 cites W2109235804 @default.
• W2897313170 cites W2109743529 @default.
• W2897313170 cites W2111579412 @default.
• W2897313170 cites W2112545207 @default.
• W2897313170 cites W2116148865 @default.
• W2897313170 cites W2118563516 @default.
• W2897313170 cites W2122789001 @default.
• W2897313170 cites W2123395972 @default.
• W2897313170 cites W2128659236 @default.
• W2897313170 cites W2129809168 @default.
• W2897313170 cites W2137557016 @default.
• W2897313170 cites W2138995291 @default.
• W2897313170 cites W2144902422 @default.
• W2897313170 cites W2145295623 @default.
• W2897313170 cites W2147854592 @default.
• W2897313170 cites W2151693816 @default.
• W2897313170 cites W2160840682 @default.
• W2897313170 cites W2164535072 @default.
• W2897313170 cites W2171188027 @default.
• W2897313170 cites W2172039283 @default.
• W2897313170 cites W2290902083 @default.
• W2897313170 cites W2295780565 @default.
• W2897313170 cites W2544176167 @default.
• W2897313170 cites W2549898883 @default.
• W2897313170 cites W2554443946 @default.
• W2897313170 cites W2579923771 @default.
• W2897313170 cites W2590518419 @default.
• W2897313170 cites W2806703135 @default.
• W2897313170 cites W2912578778 @default.
• W2897313170 cites W2962840796 @default.
• W2897313170 cites W2962910688 @default.
• W2897313170 cites W2963013450 @default.
• W2897313170 cites W2963317682 @default.
• W2897313170 cites W2963389768 @default.
• W2897313170 cites W2963477567 @default.
• W2897313170 cites W2963755879 @default.
• W2897313170 cites W2964091842 @default.
• W2897313170 cites W2964153027 @default.
• W2897313170 cites W2964323789 @default.
• W2897313170 cites W2964328735 @default.
• W2897313170 hasPublicationYear "2018" @default.
• W2897313170 type Work @default.
• W2897313170 sameAs 2897313170 @default.
• W2897313170 citedByCount "0" @default.
• W2897313170 crossrefType "posted-content" @default.
• W2897313170 hasAuthorship W2897313170A5020766546 @default.
• W2897313170 hasAuthorship W2897313170A5040922600 @default.
• W2897313170 hasConcept C11413529 @default.
• W2897313170 hasConcept C118615104 @default.
• W2897313170 hasConcept C122383733 @default.
• W2897313170 hasConcept C126255220 @default.
• W2897313170 hasConcept C134306372 @default.
• W2897313170 hasConcept C138885662 @default.
• W2897313170 hasConcept C154945302 @default.
• W2897313170 hasConcept C162324750 @default.
• W2897313170 hasConcept C176217482 @default.
• W2897313170 hasConcept C177264268 @default.
• W2897313170 hasConcept C199360897 @default.
• W2897313170 hasConcept C202444582 @default.
• W2897313170 hasConcept C21547014 @default.
• W2897313170 hasConcept C2776401178 @default.
• W2897313170 hasConcept C33676613 @default.
• W2897313170 hasConcept C33923547 @default.
• W2897313170 hasConcept C41008148 @default.
• W2897313170 hasConcept C41895202 @default.
• W2897313170 hasConcept C51823790 @default.
• W2897313170 hasConcept C62799726 @default.
• W2897313170 hasConcept C74193536 @default.
• W2897313170 hasConcept C80884492 @default.
• W2897313170 hasConcept C83665646 @default.
• W2897313170 hasConceptScore W2897313170C11413529 @default.
• W2897313170 hasConceptScore W2897313170C118615104 @default.
• W2897313170 hasConceptScore W2897313170C122383733 @default.
• W2897313170 hasConceptScore W2897313170C126255220 @default.
• W2897313170 hasConceptScore W2897313170C134306372 @default.
• W2897313170 hasConceptScore W2897313170C138885662 @default.
• W2897313170 hasConceptScore W2897313170C154945302 @default.
• W2897313170 hasConceptScore W2897313170C162324750 @default.
• W2897313170 hasConceptScore W2897313170C176217482 @default.
• W2897313170 hasConceptScore W2897313170C177264268 @default.
• W2897313170 hasConceptScore W2897313170C199360897 @default.
• W2897313170 hasConceptScore W2897313170C202444582 @default.

• next