Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387293460> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4387293460 abstract "We introduce a new tool, Transductive Local Rademacher Complexity (TLRC), to analyze the generalization performance of transductive learning methods and motivate new transductive learning algorithms. Our work extends the idea of the popular Local Rademacher Complexity (LRC) to the transductive setting with considerable changes compared to the analysis of typical LRC methods in the inductive setting. We present a localized version of Rademacher complexity based tool wihch can be applied to various transductive learning problems and gain sharp bounds under proper conditions. Similar to the development of LRC, we build TLRC by starting from a sharp concentration inequality for independent variables with variance information. The prediction function class of a transductive learning model is then divided into pieces with a sub-root function being the upper bound for the Rademacher complexity of each piece, and the variance of all the functions in each piece is limited. A carefully designed variance operator is used to ensure that the bound for the test loss on unlabeled test data in the transductive setting enjoys a remarkable similarity to that of the classical LRC bound in the inductive setting. We use the new TLRC tool to analyze the Transductive Kernel Learning (TKL) model, where the labels of test data are generated by a kernel function. The result of TKL lays the foundation for generalization bounds for two types of transductive learning tasks, Graph Transductive Learning (GTL) and Transductive Nonparametric Kernel Regression (TNKR). When the target function is low-dimensional or approximately low-dimensional, we design low rank methods for both GTL and TNKR, which enjoy particularly sharper generalization bounds by TLRC which cannot be achieved by existing learning theory methods, to the best of our knowledge." @default.
- W4387293460 created "2023-10-03" @default.
- W4387293460 creator A5012971809 @default.
- W4387293460 date "2023-09-28" @default.
- W4387293460 modified "2023-10-04" @default.
- W4387293460 title "Sharp Generalization of Transductive Learning: A Transductive Local Rademacher Complexity Approach" @default.
- W4387293460 doi "https://doi.org/10.48550/arxiv.2309.16858" @default.
- W4387293460 hasPublicationYear "2023" @default.
- W4387293460 type Work @default.
- W4387293460 citedByCount "0" @default.
- W4387293460 crossrefType "posted-content" @default.
- W4387293460 hasAuthorship W4387293460A5012971809 @default.
- W4387293460 hasBestOaLocation W43872934601 @default.
- W4387293460 hasConcept C119857082 @default.
- W4387293460 hasConcept C121955636 @default.
- W4387293460 hasConcept C134306372 @default.
- W4387293460 hasConcept C14036430 @default.
- W4387293460 hasConcept C144133560 @default.
- W4387293460 hasConcept C15152581 @default.
- W4387293460 hasConcept C154945302 @default.
- W4387293460 hasConcept C177148314 @default.
- W4387293460 hasConcept C185592680 @default.
- W4387293460 hasConcept C196083921 @default.
- W4387293460 hasConcept C33923547 @default.
- W4387293460 hasConcept C41008148 @default.
- W4387293460 hasConcept C55493867 @default.
- W4387293460 hasConcept C58973888 @default.
- W4387293460 hasConcept C77553402 @default.
- W4387293460 hasConcept C78458016 @default.
- W4387293460 hasConcept C86803240 @default.
- W4387293460 hasConceptScore W4387293460C119857082 @default.
- W4387293460 hasConceptScore W4387293460C121955636 @default.
- W4387293460 hasConceptScore W4387293460C134306372 @default.
- W4387293460 hasConceptScore W4387293460C14036430 @default.
- W4387293460 hasConceptScore W4387293460C144133560 @default.
- W4387293460 hasConceptScore W4387293460C15152581 @default.
- W4387293460 hasConceptScore W4387293460C154945302 @default.
- W4387293460 hasConceptScore W4387293460C177148314 @default.
- W4387293460 hasConceptScore W4387293460C185592680 @default.
- W4387293460 hasConceptScore W4387293460C196083921 @default.
- W4387293460 hasConceptScore W4387293460C33923547 @default.
- W4387293460 hasConceptScore W4387293460C41008148 @default.
- W4387293460 hasConceptScore W4387293460C55493867 @default.
- W4387293460 hasConceptScore W4387293460C58973888 @default.
- W4387293460 hasConceptScore W4387293460C77553402 @default.
- W4387293460 hasConceptScore W4387293460C78458016 @default.
- W4387293460 hasConceptScore W4387293460C86803240 @default.
- W4387293460 hasLocation W43872934601 @default.
- W4387293460 hasOpenAccess W4387293460 @default.
- W4387293460 hasPrimaryLocation W43872934601 @default.
- W4387293460 hasRelatedWork W2795261237 @default.
- W4387293460 hasRelatedWork W3025582806 @default.
- W4387293460 hasRelatedWork W3094076422 @default.
- W4387293460 hasRelatedWork W3162567751 @default.
- W4387293460 hasRelatedWork W3196155444 @default.
- W4387293460 hasRelatedWork W4285260836 @default.
- W4387293460 hasRelatedWork W4306321456 @default.
- W4387293460 hasRelatedWork W4319309271 @default.
- W4387293460 hasRelatedWork W4320063314 @default.
- W4387293460 hasRelatedWork W4386025632 @default.
- W4387293460 isParatext "false" @default.
- W4387293460 isRetracted "false" @default.
- W4387293460 workType "article" @default.