Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893133352> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2893133352 abstract "Author(s): Rahmanian, Holakou | Advisor(s): Warmuth, Manfred K; Vishwanathan, SVN | Abstract: This thesis develops algorithms for learning combinatorial objects. A combinatorial object is a structured concept composed of components. Examples are permutations, Huffman trees, binary search trees and paths in a directed graph. Learning combinatorial objects is a challenging problem: First, the number of combinatorial objects is typically exponential in terms of number of components. Second, the convex hull of these objects is a polytope whose characterization in the original space may have exponentially many facets or a description of the polytope in terms of facets/inequalities may not be even known. Finally, the loss of each object could be a complicated function of its component and may not be simply additive as a function of the components. In this thesis, we explore a wide variety of combinatorial objects and address the challenges above. For each combinatorial object, we go beyond the original space of the problem and introduce auxiliary spaces and representations. The representation of the objects in these auxiliary spaces admits additive losses and polytopes with polynomially many facets. This allows us to extend well-known algorithms like Expanded Hedge and Component Hedge to these combinatorial objects for the first time." @default.
- W2893133352 created "2018-10-05" @default.
- W2893133352 creator A5086618139 @default.
- W2893133352 date "2018-01-01" @default.
- W2893133352 modified "2023-09-26" @default.
- W2893133352 title "Online Learning of Combinatorial Objects" @default.
- W2893133352 hasPublicationYear "2018" @default.
- W2893133352 type Work @default.
- W2893133352 sameAs 2893133352 @default.
- W2893133352 citedByCount "0" @default.
- W2893133352 crossrefType "journal-article" @default.
- W2893133352 hasAuthorship W2893133352A5086618139 @default.
- W2893133352 hasConcept C112680207 @default.
- W2893133352 hasConcept C11413529 @default.
- W2893133352 hasConcept C114614502 @default.
- W2893133352 hasConcept C115908005 @default.
- W2893133352 hasConcept C145691206 @default.
- W2893133352 hasConcept C154945302 @default.
- W2893133352 hasConcept C17744445 @default.
- W2893133352 hasConcept C199539241 @default.
- W2893133352 hasConcept C206194317 @default.
- W2893133352 hasConcept C2524010 @default.
- W2893133352 hasConcept C2776359362 @default.
- W2893133352 hasConcept C2781238097 @default.
- W2893133352 hasConcept C33923547 @default.
- W2893133352 hasConcept C41008148 @default.
- W2893133352 hasConcept C52692508 @default.
- W2893133352 hasConcept C54829058 @default.
- W2893133352 hasConcept C80444323 @default.
- W2893133352 hasConcept C94625758 @default.
- W2893133352 hasConceptScore W2893133352C112680207 @default.
- W2893133352 hasConceptScore W2893133352C11413529 @default.
- W2893133352 hasConceptScore W2893133352C114614502 @default.
- W2893133352 hasConceptScore W2893133352C115908005 @default.
- W2893133352 hasConceptScore W2893133352C145691206 @default.
- W2893133352 hasConceptScore W2893133352C154945302 @default.
- W2893133352 hasConceptScore W2893133352C17744445 @default.
- W2893133352 hasConceptScore W2893133352C199539241 @default.
- W2893133352 hasConceptScore W2893133352C206194317 @default.
- W2893133352 hasConceptScore W2893133352C2524010 @default.
- W2893133352 hasConceptScore W2893133352C2776359362 @default.
- W2893133352 hasConceptScore W2893133352C2781238097 @default.
- W2893133352 hasConceptScore W2893133352C33923547 @default.
- W2893133352 hasConceptScore W2893133352C41008148 @default.
- W2893133352 hasConceptScore W2893133352C52692508 @default.
- W2893133352 hasConceptScore W2893133352C54829058 @default.
- W2893133352 hasConceptScore W2893133352C80444323 @default.
- W2893133352 hasConceptScore W2893133352C94625758 @default.
- W2893133352 hasLocation W28931333521 @default.
- W2893133352 hasOpenAccess W2893133352 @default.
- W2893133352 hasPrimaryLocation W28931333521 @default.
- W2893133352 hasRelatedWork W1131085401 @default.
- W2893133352 hasRelatedWork W139939626 @default.
- W2893133352 hasRelatedWork W1512172501 @default.
- W2893133352 hasRelatedWork W1519567032 @default.
- W2893133352 hasRelatedWork W1532962737 @default.
- W2893133352 hasRelatedWork W1575764817 @default.
- W2893133352 hasRelatedWork W1980081377 @default.
- W2893133352 hasRelatedWork W1984090248 @default.
- W2893133352 hasRelatedWork W1993214427 @default.
- W2893133352 hasRelatedWork W2095594256 @default.
- W2893133352 hasRelatedWork W2132153047 @default.
- W2893133352 hasRelatedWork W2149907923 @default.
- W2893133352 hasRelatedWork W2498623144 @default.
- W2893133352 hasRelatedWork W2611986269 @default.
- W2893133352 hasRelatedWork W2924720492 @default.
- W2893133352 hasRelatedWork W2949766608 @default.
- W2893133352 hasRelatedWork W3015210145 @default.
- W2893133352 hasRelatedWork W3129588812 @default.
- W2893133352 hasRelatedWork W3177370958 @default.
- W2893133352 hasRelatedWork W1940064195 @default.
- W2893133352 isParatext "false" @default.
- W2893133352 isRetracted "false" @default.
- W2893133352 magId "2893133352" @default.
- W2893133352 workType "article" @default.