Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321162010> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4321162010 abstract "Decision Trees are some of the most popular machine learning models today due to their out-of-the-box performance and interpretability. Often, Decision Trees models are constructed greedily in a top-down fashion via heuristic search criteria, such as Gini impurity or entropy. However, trees constructed in this manner are sensitive to minor fluctuations in training data and are prone to overfitting. In contrast, Bayesian approaches to tree construction formulate the selection process as a posterior inference problem; such approaches are more stable and provide greater theoretical guarantees. However, generating Bayesian Decision Trees usually requires sampling from complex, multimodal posterior distributions. Current Markov Chain Monte Carlo-based approaches for sampling Bayesian Decision Trees are prone to mode collapse and long mixing times, which makes them impractical. In this paper, we propose a new criterion for training Bayesian Decision Trees. Our criterion gives rise to BCART-PCFG, which can efficiently sample decision trees from a posterior distribution across trees given the data and find the maximum a posteriori (MAP) tree. Learning the posterior and training the sampler can be done in time that is polynomial in the dataset size. Once the posterior has been learned, trees can be sampled efficiently (linearly in the number of nodes). At the core of our method is a reduction of sampling the posterior to sampling a derivation from a probabilistic context-free grammar. We find that trees sampled via BCART-PCFG perform comparable to or better than greedily-constructed Decision Trees in classification accuracy on several datasets. Additionally, the trees sampled via BCART-PCFG are significantly smaller -- sometimes by as much as 20x." @default.
- W4321162010 created "2023-02-18" @default.
- W4321162010 creator A5036036404 @default.
- W4321162010 creator A5066710774 @default.
- W4321162010 creator A5068859532 @default.
- W4321162010 creator A5074969309 @default.
- W4321162010 date "2023-02-14" @default.
- W4321162010 modified "2023-09-29" @default.
- W4321162010 title "Bayesian Decision Trees via Tractable Priors and Probabilistic Context-Free Grammars" @default.
- W4321162010 doi "https://doi.org/10.48550/arxiv.2302.07407" @default.
- W4321162010 hasPublicationYear "2023" @default.
- W4321162010 type Work @default.
- W4321162010 citedByCount "0" @default.
- W4321162010 crossrefType "posted-content" @default.
- W4321162010 hasAuthorship W4321162010A5036036404 @default.
- W4321162010 hasAuthorship W4321162010A5066710774 @default.
- W4321162010 hasAuthorship W4321162010A5068859532 @default.
- W4321162010 hasAuthorship W4321162010A5074969309 @default.
- W4321162010 hasBestOaLocation W43211620101 @default.
- W4321162010 hasConcept C10229987 @default.
- W4321162010 hasConcept C107673813 @default.
- W4321162010 hasConcept C111350023 @default.
- W4321162010 hasConcept C119857082 @default.
- W4321162010 hasConcept C154945302 @default.
- W4321162010 hasConcept C22019652 @default.
- W4321162010 hasConcept C41008148 @default.
- W4321162010 hasConcept C50644808 @default.
- W4321162010 hasConcept C5481197 @default.
- W4321162010 hasConcept C57830394 @default.
- W4321162010 hasConcept C84525736 @default.
- W4321162010 hasConceptScore W4321162010C10229987 @default.
- W4321162010 hasConceptScore W4321162010C107673813 @default.
- W4321162010 hasConceptScore W4321162010C111350023 @default.
- W4321162010 hasConceptScore W4321162010C119857082 @default.
- W4321162010 hasConceptScore W4321162010C154945302 @default.
- W4321162010 hasConceptScore W4321162010C22019652 @default.
- W4321162010 hasConceptScore W4321162010C41008148 @default.
- W4321162010 hasConceptScore W4321162010C50644808 @default.
- W4321162010 hasConceptScore W4321162010C5481197 @default.
- W4321162010 hasConceptScore W4321162010C57830394 @default.
- W4321162010 hasConceptScore W4321162010C84525736 @default.
- W4321162010 hasLocation W43211620101 @default.
- W4321162010 hasOpenAccess W4321162010 @default.
- W4321162010 hasPrimaryLocation W43211620101 @default.
- W4321162010 hasRelatedWork W1554219991 @default.
- W4321162010 hasRelatedWork W1979441003 @default.
- W4321162010 hasRelatedWork W2242235392 @default.
- W4321162010 hasRelatedWork W2617799811 @default.
- W4321162010 hasRelatedWork W2909800806 @default.
- W4321162010 hasRelatedWork W2962772147 @default.
- W4321162010 hasRelatedWork W2999056919 @default.
- W4321162010 hasRelatedWork W3125006864 @default.
- W4321162010 hasRelatedWork W3135874320 @default.
- W4321162010 hasRelatedWork W4288336439 @default.
- W4321162010 isParatext "false" @default.
- W4321162010 isRetracted "false" @default.
- W4321162010 workType "article" @default.