Matches in SemOpenAlex for { <https://semopenalex.org/work/W2910589780> ?p ?o ?g. }
- W2910589780 abstract "We develop fast algorithms for solving the variational and game-theoretic $p$-Laplace equations on weighted graphs for $p>2$. The graph $p$-Laplacian for $p>2$ has been proposed recently as a replacement for the standard ($p=2$) graph Laplacian in semi-supervised learning problems with very few labels, where the minimizer of the graph Laplacian becomes degenerate. We present several efficient and scalable algorithms for both the variational and game-theoretic formulations, and present numerical results on synthetic data and real data that illustrate the effectiveness of the $p$-Laplacian formulation for semi-supervised learning with few labels. We also prove new discrete to continuum convergence results for $p$-Laplace problems on $k$-nearest neighbor ($k$-NN) graphs, which are more commonly used in practice than random geometric graphs. Our analysis shows that, on $k$-NN graphs, the $p$-Laplacian retains information about the data distribution as $pto infty$ and Lipschitz learning ($p=infty$) is sensitive to the data distribution. This situation can be contrasted with random geometric graphs, where the $p$-Laplacian emph{forgets} the data distribution as $pto infty$. Finally, we give a general framework for proving discrete to continuum convergence results in graph-based learning that only requires pointwise consistency and a type of monotonicity." @default.
- W2910589780 created "2019-01-25" @default.
- W2910589780 creator A5021479136 @default.
- W2910589780 creator A5066156899 @default.
- W2910589780 creator A5088795209 @default.
- W2910589780 date "2019-01-15" @default.
- W2910589780 modified "2023-10-15" @default.
- W2910589780 title "Algorithms for $ell_p$-based semi-supervised learning on graphs" @default.
- W2910589780 cites W1479807131 @default.
- W2910589780 cites W1486280163 @default.
- W2910589780 cites W1529879082 @default.
- W2910589780 cites W1826824261 @default.
- W2910589780 cites W189343201 @default.
- W2910589780 cites W1979463344 @default.
- W2910589780 cites W1982410540 @default.
- W2910589780 cites W1991061880 @default.
- W2910589780 cites W2002182424 @default.
- W2910589780 cites W2032316144 @default.
- W2910589780 cites W2039118116 @default.
- W2910589780 cites W2039313011 @default.
- W2910589780 cites W2066590618 @default.
- W2910589780 cites W2072072671 @default.
- W2910589780 cites W2090936839 @default.
- W2910589780 cites W2096633276 @default.
- W2910589780 cites W2103829273 @default.
- W2910589780 cites W2107503465 @default.
- W2910589780 cites W2112796928 @default.
- W2910589780 cites W2119451546 @default.
- W2910589780 cites W2125407560 @default.
- W2910589780 cites W2131791003 @default.
- W2910589780 cites W2139823104 @default.
- W2910589780 cites W2140153041 @default.
- W2910589780 cites W2141088152 @default.
- W2910589780 cites W2143420533 @default.
- W2910589780 cites W2154455818 @default.
- W2910589780 cites W2165922980 @default.
- W2910589780 cites W2170155528 @default.
- W2910589780 cites W2177195156 @default.
- W2910589780 cites W2188059037 @default.
- W2910589780 cites W2210625349 @default.
- W2910589780 cites W2326915604 @default.
- W2910589780 cites W2510863276 @default.
- W2910589780 cites W2604163838 @default.
- W2910589780 cites W2730726820 @default.
- W2910589780 cites W2734358244 @default.
- W2910589780 cites W2750384547 @default.
- W2910589780 cites W2899203342 @default.
- W2910589780 cites W2912554888 @default.
- W2910589780 cites W2947904174 @default.
- W2910589780 cites W2952521183 @default.
- W2910589780 cites W2962701197 @default.
- W2910589780 cites W2962720813 @default.
- W2910589780 cites W2962826709 @default.
- W2910589780 cites W2963144360 @default.
- W2910589780 cites W2963182236 @default.
- W2910589780 cites W2970344166 @default.
- W2910589780 cites W2982315984 @default.
- W2910589780 cites W2992402078 @default.
- W2910589780 cites W2993986630 @default.
- W2910589780 cites W3152373931 @default.
- W2910589780 cites W585462275 @default.
- W2910589780 hasPublicationYear "2019" @default.
- W2910589780 type Work @default.
- W2910589780 sameAs 2910589780 @default.
- W2910589780 citedByCount "5" @default.
- W2910589780 countsByYear W29105897802019 @default.
- W2910589780 countsByYear W29105897802020 @default.
- W2910589780 countsByYear W29105897802021 @default.
- W2910589780 crossrefType "posted-content" @default.
- W2910589780 hasAuthorship W2910589780A5021479136 @default.
- W2910589780 hasAuthorship W2910589780A5066156899 @default.
- W2910589780 hasAuthorship W2910589780A5088795209 @default.
- W2910589780 hasConcept C114614502 @default.
- W2910589780 hasConcept C115178988 @default.
- W2910589780 hasConcept C118615104 @default.
- W2910589780 hasConcept C132525143 @default.
- W2910589780 hasConcept C134306372 @default.
- W2910589780 hasConcept C165700671 @default.
- W2910589780 hasConcept C202444582 @default.
- W2910589780 hasConcept C22324862 @default.
- W2910589780 hasConcept C2777984123 @default.
- W2910589780 hasConcept C33923547 @default.
- W2910589780 hasConcept C47458327 @default.
- W2910589780 hasConceptScore W2910589780C114614502 @default.
- W2910589780 hasConceptScore W2910589780C115178988 @default.
- W2910589780 hasConceptScore W2910589780C118615104 @default.
- W2910589780 hasConceptScore W2910589780C132525143 @default.
- W2910589780 hasConceptScore W2910589780C134306372 @default.
- W2910589780 hasConceptScore W2910589780C165700671 @default.
- W2910589780 hasConceptScore W2910589780C202444582 @default.
- W2910589780 hasConceptScore W2910589780C22324862 @default.
- W2910589780 hasConceptScore W2910589780C2777984123 @default.
- W2910589780 hasConceptScore W2910589780C33923547 @default.
- W2910589780 hasConceptScore W2910589780C47458327 @default.
- W2910589780 hasLocation W29105897801 @default.
- W2910589780 hasOpenAccess W2910589780 @default.
- W2910589780 hasPrimaryLocation W29105897801 @default.
- W2910589780 hasRelatedWork W1984032850 @default.
- W2910589780 hasRelatedWork W1989368986 @default.
- W2910589780 hasRelatedWork W2002276939 @default.