Matches in SemOpenAlex for { <https://semopenalex.org/work/W3112267214> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3112267214 abstract "Meta-Learning has gained increasing attention in the machine learning and artificial intelligence communities. In this paper, we introduce and study an adaptive submodular meta-learning problem. The input of our problem is a set of items, where each item has a random state which is initially unknown. The only way to observe an item's state is to select that item. Our objective is to adaptively select a group of items that achieve the best performance over a set of tasks, where each task is represented as an adaptive submodular function that maps sets of items and their states to a real number. To reduce the computational cost while maintaining a personalized solution for each future task, we first select an initial solution set based on previously observed tasks, then adaptively add the remaining items to the initial solution set when a new task arrives. As compared to the solution where a brand new solution is computed for each new task, our meta-learning based approach leads to lower computational overhead at test time since the initial solution set is pre-computed in the training stage. To solve this problem, we propose a two-phase greedy policy and show that it achieves a $1/2$ approximation ratio for the monotone case. For the non-monotone case, we develop a two-phase randomized greedy policy that achieves a $1/32$ approximation ratio." @default.
- W3112267214 created "2020-12-21" @default.
- W3112267214 creator A5050393292 @default.
- W3112267214 creator A5056375343 @default.
- W3112267214 date "2020-12-11" @default.
- W3112267214 modified "2023-09-27" @default.
- W3112267214 title "Adaptive Submodular Meta-Learning." @default.
- W3112267214 cites W1680189815 @default.
- W3112267214 cites W2042932437 @default.
- W3112267214 cites W2139238311 @default.
- W3112267214 cites W2168416649 @default.
- W3112267214 cites W2263717697 @default.
- W3112267214 cites W2272986348 @default.
- W3112267214 cites W2578206533 @default.
- W3112267214 cites W2601450892 @default.
- W3112267214 cites W2604763608 @default.
- W3112267214 cites W2735579742 @default.
- W3112267214 cites W2809246871 @default.
- W3112267214 cites W2962795549 @default.
- W3112267214 cites W2970345470 @default.
- W3112267214 cites W3005787005 @default.
- W3112267214 cites W3048806178 @default.
- W3112267214 cites W3106108463 @default.
- W3112267214 cites W99485931 @default.
- W3112267214 hasPublicationYear "2020" @default.
- W3112267214 type Work @default.
- W3112267214 sameAs 3112267214 @default.
- W3112267214 citedByCount "0" @default.
- W3112267214 crossrefType "posted-content" @default.
- W3112267214 hasAuthorship W3112267214A5050393292 @default.
- W3112267214 hasAuthorship W3112267214A5056375343 @default.
- W3112267214 hasConcept C119857082 @default.
- W3112267214 hasConcept C126255220 @default.
- W3112267214 hasConcept C15312841 @default.
- W3112267214 hasConcept C154945302 @default.
- W3112267214 hasConcept C162324750 @default.
- W3112267214 hasConcept C177264268 @default.
- W3112267214 hasConcept C178621042 @default.
- W3112267214 hasConcept C187736073 @default.
- W3112267214 hasConcept C199360897 @default.
- W3112267214 hasConcept C2524010 @default.
- W3112267214 hasConcept C2780451532 @default.
- W3112267214 hasConcept C2834757 @default.
- W3112267214 hasConcept C33923547 @default.
- W3112267214 hasConcept C41008148 @default.
- W3112267214 hasConceptScore W3112267214C119857082 @default.
- W3112267214 hasConceptScore W3112267214C126255220 @default.
- W3112267214 hasConceptScore W3112267214C15312841 @default.
- W3112267214 hasConceptScore W3112267214C154945302 @default.
- W3112267214 hasConceptScore W3112267214C162324750 @default.
- W3112267214 hasConceptScore W3112267214C177264268 @default.
- W3112267214 hasConceptScore W3112267214C178621042 @default.
- W3112267214 hasConceptScore W3112267214C187736073 @default.
- W3112267214 hasConceptScore W3112267214C199360897 @default.
- W3112267214 hasConceptScore W3112267214C2524010 @default.
- W3112267214 hasConceptScore W3112267214C2780451532 @default.
- W3112267214 hasConceptScore W3112267214C2834757 @default.
- W3112267214 hasConceptScore W3112267214C33923547 @default.
- W3112267214 hasConceptScore W3112267214C41008148 @default.
- W3112267214 hasLocation W31122672141 @default.
- W3112267214 hasOpenAccess W3112267214 @default.
- W3112267214 hasPrimaryLocation W31122672141 @default.
- W3112267214 hasRelatedWork W1672367318 @default.
- W3112267214 hasRelatedWork W2118980425 @default.
- W3112267214 hasRelatedWork W2144655553 @default.
- W3112267214 hasRelatedWork W2286947585 @default.
- W3112267214 hasRelatedWork W2398490066 @default.
- W3112267214 hasRelatedWork W2604921058 @default.
- W3112267214 hasRelatedWork W2767419258 @default.
- W3112267214 hasRelatedWork W2783634529 @default.
- W3112267214 hasRelatedWork W2891645069 @default.
- W3112267214 hasRelatedWork W2953292661 @default.
- W3112267214 hasRelatedWork W2963649256 @default.
- W3112267214 hasRelatedWork W2997729838 @default.
- W3112267214 hasRelatedWork W3014289027 @default.
- W3112267214 hasRelatedWork W3037388097 @default.
- W3112267214 hasRelatedWork W3104364497 @default.
- W3112267214 hasRelatedWork W3118694267 @default.
- W3112267214 hasRelatedWork W3182782565 @default.
- W3112267214 hasRelatedWork W3202945361 @default.
- W3112267214 hasRelatedWork W3208761439 @default.
- W3112267214 hasRelatedWork W2188102409 @default.
- W3112267214 isParatext "false" @default.
- W3112267214 isRetracted "false" @default.
- W3112267214 magId "3112267214" @default.
- W3112267214 workType "article" @default.