FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2585994070> ?p ?o ?g. }

• W2585994070 abstract "In this paper, we address learning problems for high dimensional data. Previously, oblivious random projection based approaches that project high dimensional features onto a random subspace have been used in practice for tackling high-dimensionality challenge in machine learning. Recently, various non-oblivious randomized reduction methods have been developed and deployed for solving many numerical problems such as matrix product approximation, low-rank matrix approximation, etc. However, they are less explored for the machine learning tasks, e.g., classification. More seriously, the theoretical analysis of excess risk bounds for risk minimization, an important measure of generalization performance, has not been established for non-oblivious randomized reduction methods. It therefore remains an open problem what is the benefit of using them over previous oblivious random projection based approaches. To tackle these challenges, we propose an algorithmic framework for employing non-oblivious randomized reduction method for general empirical risk minimizing in machine learning tasks, where the original high-dimensional features are projected onto a random subspace that is derived from the data with a small matrix approximation error. We then derive the first excess risk bound for the proposed non-oblivious randomized reduction approach without requiring strong assumptions on the training data. The established excess risk bound exhibits that the proposed approach provides much better generalization performance and it also sheds more insights about different randomized reduction approaches. Finally, we conduct extensive experiments on both synthetic and real-world benchmark datasets, whose dimension scales to O(10^7), to demonstrate the efficacy of our proposed approach." @default.
• W2585994070 created "2017-02-10" @default.
• W2585994070 creator A5018343158 @default.
• W2585994070 creator A5023288846 @default.
• W2585994070 creator A5081589298 @default.
• W2585994070 creator A5081662508 @default.
• W2585994070 date "2017-02-13" @default.
• W2585994070 modified "2023-10-18" @default.
• W2585994070 title "Efficient Non-Oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee" @default.
• W2585994070 cites W1486890033 @default.
• W2585994070 cites W1788183014 @default.
• W2585994070 cites W1945899805 @default.
• W2585994070 cites W2088658556 @default.
• W2585994070 cites W2104624965 @default.
• W2585994070 cites W2107791152 @default.
• W2585994070 cites W2111296615 @default.
• W2585994070 cites W2114609025 @default.
• W2585994070 cites W2148603752 @default.
• W2585994070 cites W2171810522 @default.
• W2585994070 cites W2185932763 @default.
• W2585994070 cites W2616038372 @default.
• W2585994070 cites W2949809202 @default.
• W2585994070 cites W2950718103 @default.
• W2585994070 cites W2951228652 @default.
• W2585994070 cites W2951863880 @default.
• W2585994070 cites W2963459305 @default.
• W2585994070 cites W826455576 @default.
• W2585994070 doi "https://doi.org/10.1609/aaai.v31i1.10845" @default.
• W2585994070 hasPublicationYear "2017" @default.
• W2585994070 type Work @default.
• W2585994070 sameAs 2585994070 @default.
• W2585994070 citedByCount "0" @default.
• W2585994070 crossrefType "journal-article" @default.
• W2585994070 hasAuthorship W2585994070A5018343158 @default.
• W2585994070 hasAuthorship W2585994070A5023288846 @default.
• W2585994070 hasAuthorship W2585994070A5081589298 @default.
• W2585994070 hasAuthorship W2585994070A5081662508 @default.
• W2585994070 hasBestOaLocation W25859940701 @default.
• W2585994070 hasConcept C106487976 @default.
• W2585994070 hasConcept C107321475 @default.
• W2585994070 hasConcept C111335779 @default.
• W2585994070 hasConcept C11413529 @default.
• W2585994070 hasConcept C119857082 @default.
• W2585994070 hasConcept C121332964 @default.
• W2585994070 hasConcept C128669082 @default.
• W2585994070 hasConcept C13280743 @default.
• W2585994070 hasConcept C134306372 @default.
• W2585994070 hasConcept C154945302 @default.
• W2585994070 hasConcept C158693339 @default.
• W2585994070 hasConcept C159985019 @default.
• W2585994070 hasConcept C177148314 @default.
• W2585994070 hasConcept C185798385 @default.
• W2585994070 hasConcept C192562407 @default.
• W2585994070 hasConcept C205649164 @default.
• W2585994070 hasConcept C2524010 @default.
• W2585994070 hasConcept C2777036070 @default.
• W2585994070 hasConcept C32834561 @default.
• W2585994070 hasConcept C33923547 @default.
• W2585994070 hasConcept C41008148 @default.
• W2585994070 hasConcept C57493831 @default.
• W2585994070 hasConcept C62520636 @default.
• W2585994070 hasConcept C64812099 @default.
• W2585994070 hasConcept C70518039 @default.
• W2585994070 hasConceptScore W2585994070C106487976 @default.
• W2585994070 hasConceptScore W2585994070C107321475 @default.
• W2585994070 hasConceptScore W2585994070C111335779 @default.
• W2585994070 hasConceptScore W2585994070C11413529 @default.
• W2585994070 hasConceptScore W2585994070C119857082 @default.
• W2585994070 hasConceptScore W2585994070C121332964 @default.
• W2585994070 hasConceptScore W2585994070C128669082 @default.
• W2585994070 hasConceptScore W2585994070C13280743 @default.
• W2585994070 hasConceptScore W2585994070C134306372 @default.
• W2585994070 hasConceptScore W2585994070C154945302 @default.
• W2585994070 hasConceptScore W2585994070C158693339 @default.
• W2585994070 hasConceptScore W2585994070C159985019 @default.
• W2585994070 hasConceptScore W2585994070C177148314 @default.
• W2585994070 hasConceptScore W2585994070C185798385 @default.
• W2585994070 hasConceptScore W2585994070C192562407 @default.
• W2585994070 hasConceptScore W2585994070C205649164 @default.
• W2585994070 hasConceptScore W2585994070C2524010 @default.
• W2585994070 hasConceptScore W2585994070C2777036070 @default.
• W2585994070 hasConceptScore W2585994070C32834561 @default.
• W2585994070 hasConceptScore W2585994070C33923547 @default.
• W2585994070 hasConceptScore W2585994070C41008148 @default.
• W2585994070 hasConceptScore W2585994070C57493831 @default.
• W2585994070 hasConceptScore W2585994070C62520636 @default.
• W2585994070 hasConceptScore W2585994070C64812099 @default.
• W2585994070 hasConceptScore W2585994070C70518039 @default.
• W2585994070 hasIssue "1" @default.
• W2585994070 hasLocation W25859940701 @default.
• W2585994070 hasLocation W25859940702 @default.
• W2585994070 hasOpenAccess W2585994070 @default.
• W2585994070 hasPrimaryLocation W25859940701 @default.
• W2585994070 hasRelatedWork W2045648570 @default.
• W2585994070 hasRelatedWork W2089497633 @default.
• W2585994070 hasRelatedWork W2184864404 @default.
• W2585994070 hasRelatedWork W2245231753 @default.
• W2585994070 hasRelatedWork W2349719765 @default.
• W2585994070 hasRelatedWork W2585994070 @default.
• W2585994070 hasRelatedWork W2807932639 @default.

• next