Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892997046> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W2892997046 abstract "The main advantage of non-parametric models is that the accuracy of the model (degreesof freedom) adapts to the number of samples. The main drawback is the so-called curseof kernelization: to learn the model we must first compute a similarity matrix among allsamples, which requires quadratic space and time and is unfeasible for large datasets.Nonetheless the underlying effective dimension (effective d.o.f.) of the dataset is often muchsmaller than its size, and we can replace the dataset with a subset (dictionary) of highlyinformative samples. Unfortunately, fast data-oblivious selection methods (e.g., uniformsampling) almost always discard useful information, while data-adaptive methods thatprovably construct an accurate dictionary, such as ridge leverage score (RLS) sampling,have a quadratic time/space cost.In this thesis we introduce a new single-pass streaming RLS sampling approach thatsequentially construct the dictionary, where each step compares a new sample only withthe current intermediate dictionary and not all past samples. We prove that the size ofall intermediate dictionaries scales only with the effective dimension of the dataset, andtherefore guarantee a per-step time and space complexity independent from the number ofsamples. This reduces the overall time required to construct provably accurate dictionariesfrom quadratic to near-linear, or even logarithmic when parallelized.Finally, for many non-parametric learning problems (e.g., K-PCA, graph SSL, online kernellearning) we we show that we can can use the generated dictionaries to compute approximatesolutions in near-linear that are both provably accurate and empirically competitive." @default.
- W2892997046 created "2018-10-05" @default.
- W2892997046 creator A5018745259 @default.
- W2892997046 date "2017-12-18" @default.
- W2892997046 modified "2023-09-25" @default.
- W2892997046 title "Efficient sequential learning in structured and constrained environments" @default.
- W2892997046 hasPublicationYear "2017" @default.
- W2892997046 type Work @default.
- W2892997046 sameAs 2892997046 @default.
- W2892997046 citedByCount "3" @default.
- W2892997046 countsByYear W28929970462019 @default.
- W2892997046 countsByYear W28929970462020 @default.
- W2892997046 crossrefType "dissertation" @default.
- W2892997046 hasAuthorship W2892997046A5018745259 @default.
- W2892997046 hasConcept C111030470 @default.
- W2892997046 hasConcept C11413529 @default.
- W2892997046 hasConcept C129844170 @default.
- W2892997046 hasConcept C153083717 @default.
- W2892997046 hasConcept C154945302 @default.
- W2892997046 hasConcept C202444582 @default.
- W2892997046 hasConcept C2524010 @default.
- W2892997046 hasConcept C33676613 @default.
- W2892997046 hasConcept C33923547 @default.
- W2892997046 hasConcept C41008148 @default.
- W2892997046 hasConcept C80444323 @default.
- W2892997046 hasConceptScore W2892997046C111030470 @default.
- W2892997046 hasConceptScore W2892997046C11413529 @default.
- W2892997046 hasConceptScore W2892997046C129844170 @default.
- W2892997046 hasConceptScore W2892997046C153083717 @default.
- W2892997046 hasConceptScore W2892997046C154945302 @default.
- W2892997046 hasConceptScore W2892997046C202444582 @default.
- W2892997046 hasConceptScore W2892997046C2524010 @default.
- W2892997046 hasConceptScore W2892997046C33676613 @default.
- W2892997046 hasConceptScore W2892997046C33923547 @default.
- W2892997046 hasConceptScore W2892997046C41008148 @default.
- W2892997046 hasConceptScore W2892997046C80444323 @default.
- W2892997046 hasLocation W28929970461 @default.
- W2892997046 hasOpenAccess W2892997046 @default.
- W2892997046 hasPrimaryLocation W28929970461 @default.
- W2892997046 hasRelatedWork W1496805632 @default.
- W2892997046 hasRelatedWork W1585302803 @default.
- W2892997046 hasRelatedWork W2003677307 @default.
- W2892997046 hasRelatedWork W2039025536 @default.
- W2892997046 hasRelatedWork W2116133729 @default.
- W2892997046 hasRelatedWork W2278194246 @default.
- W2892997046 hasRelatedWork W2299156643 @default.
- W2892997046 hasRelatedWork W2422452261 @default.
- W2892997046 hasRelatedWork W2743943492 @default.
- W2892997046 hasRelatedWork W2786881437 @default.
- W2892997046 hasRelatedWork W2948586274 @default.
- W2892997046 hasRelatedWork W2962844620 @default.
- W2892997046 hasRelatedWork W2962887838 @default.
- W2892997046 hasRelatedWork W2963324104 @default.
- W2892997046 hasRelatedWork W2964240731 @default.
- W2892997046 hasRelatedWork W2989766428 @default.
- W2892997046 hasRelatedWork W3019216617 @default.
- W2892997046 hasRelatedWork W3104596380 @default.
- W2892997046 hasRelatedWork W3208336470 @default.
- W2892997046 hasRelatedWork W2609812562 @default.
- W2892997046 isParatext "false" @default.
- W2892997046 isRetracted "false" @default.
- W2892997046 magId "2892997046" @default.
- W2892997046 workType "dissertation" @default.