Matches in SemOpenAlex for { <https://semopenalex.org/work/W3038684703> ?p ?o ?g. }
- W3038684703 abstract "High dimensional black-box optimization has broad applications but remains a challenging problem to solve. Given a set of samples ${vx_i, y_i}$, building a global model (like Bayesian Optimization (BO)) suffers from the curse of dimensionality in the high-dimensional search space, while a greedy search may lead to sub-optimality. By recursively splitting the search space into regions with high/low function values, recent works like LaNAS shows good performance in Neural Architecture Search (NAS), reducing the sample complexity empirically. In this paper, we coin LA-MCTS that extends LaNAS to other domains. Unlike previous approaches, LA-MCTS learns the partition of the search space using a few samples and their function values in an online fashion. While LaNAS uses linear partition and performs uniform sampling in each region, our LA-MCTS adopts a nonlinear decision boundary and learns a local model to pick good candidates. If the nonlinear partition function and the local model fits well with ground-truth black-box function, then good partitions and candidates can be reached with much fewer samples. LA-MCTS serves as a emph{meta-algorithm} by using existing black-box optimizers (e.g., BO, TuRBO) as its local models, achieving strong performance in general black-box optimization and reinforcement learning benchmarks, in particular for high-dimensional problems." @default.
- W3038684703 created "2020-07-10" @default.
- W3038684703 creator A5010181097 @default.
- W3038684703 creator A5036529548 @default.
- W3038684703 creator A5084821923 @default.
- W3038684703 date "2020-07-01" @default.
- W3038684703 modified "2023-10-01" @default.
- W3038684703 title "Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search" @default.
- W3038684703 cites W1480330138 @default.
- W3038684703 cites W1512149552 @default.
- W3038684703 cites W1595159159 @default.
- W3038684703 cites W1871676304 @default.
- W3038684703 cites W1915824153 @default.
- W3038684703 cites W1925579137 @default.
- W3038684703 cites W2031715986 @default.
- W3038684703 cites W2051651878 @default.
- W3038684703 cites W2073107347 @default.
- W3038684703 cites W2083875149 @default.
- W3038684703 cites W2096678000 @default.
- W3038684703 cites W2099201756 @default.
- W3038684703 cites W2099768828 @default.
- W3038684703 cites W2106411961 @default.
- W3038684703 cites W2126316555 @default.
- W3038684703 cites W2138537392 @default.
- W3038684703 cites W2146047772 @default.
- W3038684703 cites W2156106639 @default.
- W3038684703 cites W2158782408 @default.
- W3038684703 cites W2168405694 @default.
- W3038684703 cites W2186241545 @default.
- W3038684703 cites W2187386544 @default.
- W3038684703 cites W2192203593 @default.
- W3038684703 cites W2257979135 @default.
- W3038684703 cites W2399790246 @default.
- W3038684703 cites W2553303224 @default.
- W3038684703 cites W2556372419 @default.
- W3038684703 cites W2571670780 @default.
- W3038684703 cites W2584555500 @default.
- W3038684703 cites W2596367596 @default.
- W3038684703 cites W2622730215 @default.
- W3038684703 cites W2766447205 @default.
- W3038684703 cites W2783201493 @default.
- W3038684703 cites W2788642651 @default.
- W3038684703 cites W2789525339 @default.
- W3038684703 cites W2803461142 @default.
- W3038684703 cites W2873705236 @default.
- W3038684703 cites W2890055393 @default.
- W3038684703 cites W2945677399 @default.
- W3038684703 cites W2952490571 @default.
- W3038684703 cites W2952677397 @default.
- W3038684703 cites W2953083211 @default.
- W3038684703 cites W2962749646 @default.
- W3038684703 cites W2962753844 @default.
- W3038684703 cites W2963423218 @default.
- W3038684703 cites W2963659022 @default.
- W3038684703 cites W2963815651 @default.
- W3038684703 cites W2964096186 @default.
- W3038684703 cites W2969999645 @default.
- W3038684703 cites W2980498459 @default.
- W3038684703 cites W2998394761 @default.
- W3038684703 cites W3018195242 @default.
- W3038684703 cites W3039845339 @default.
- W3038684703 cites W3118210634 @default.
- W3038684703 cites W60686164 @default.
- W3038684703 hasPublicationYear "2020" @default.
- W3038684703 type Work @default.
- W3038684703 sameAs 3038684703 @default.
- W3038684703 citedByCount "11" @default.
- W3038684703 countsByYear W30386847032020 @default.
- W3038684703 countsByYear W30386847032021 @default.
- W3038684703 crossrefType "posted-content" @default.
- W3038684703 hasAuthorship W3038684703A5010181097 @default.
- W3038684703 hasAuthorship W3038684703A5036529548 @default.
- W3038684703 hasAuthorship W3038684703A5084821923 @default.
- W3038684703 hasConcept C105795698 @default.
- W3038684703 hasConcept C111030470 @default.
- W3038684703 hasConcept C11413529 @default.
- W3038684703 hasConcept C114614502 @default.
- W3038684703 hasConcept C126255220 @default.
- W3038684703 hasConcept C154945302 @default.
- W3038684703 hasConcept C19499675 @default.
- W3038684703 hasConcept C2778049539 @default.
- W3038684703 hasConcept C33923547 @default.
- W3038684703 hasConcept C41008148 @default.
- W3038684703 hasConcept C42812 @default.
- W3038684703 hasConcept C46149586 @default.
- W3038684703 hasConcept C94966114 @default.
- W3038684703 hasConceptScore W3038684703C105795698 @default.
- W3038684703 hasConceptScore W3038684703C111030470 @default.
- W3038684703 hasConceptScore W3038684703C11413529 @default.
- W3038684703 hasConceptScore W3038684703C114614502 @default.
- W3038684703 hasConceptScore W3038684703C126255220 @default.
- W3038684703 hasConceptScore W3038684703C154945302 @default.
- W3038684703 hasConceptScore W3038684703C19499675 @default.
- W3038684703 hasConceptScore W3038684703C2778049539 @default.
- W3038684703 hasConceptScore W3038684703C33923547 @default.
- W3038684703 hasConceptScore W3038684703C41008148 @default.
- W3038684703 hasConceptScore W3038684703C42812 @default.
- W3038684703 hasConceptScore W3038684703C46149586 @default.
- W3038684703 hasConceptScore W3038684703C94966114 @default.
- W3038684703 hasLocation W30386847031 @default.