AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

BAST: Bayesian Additive Regression Spanning Trees for Complex Constrained Domain

Zhao Tang Luo, Huiyan Sang, Bani Mallick

NeurIPS 2021 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use BAST (random spanning tree partitions) instead of BART binary tree partitionsBAST · U-shape domain, sigma=0.1MSPE: 1.541 -> 0.189Improved
Use BAST instead of BARTBAST · U-shape domain, sigma=1MSPE: 2.650 -> 1.283Improved
Use BAST instead of soap film smoothing (SFS)BAST · U-shape domain, sigma=0.5MAPE: 0.591 -> 0.491Improved
Use BAST instead of sparse inGPBAST · U-shape domain, sigma=0.1MSPE: 0.814 -> 0.189Improved
Use BAST instead of BART on probabilistic predictionBAST · U-shape domain, sigma=0.5Mean CRPS: 0.575 -> 0.371Improved
Use BAST instead of BART on a bitten torus manifoldBAST · Bitten torus, sigma=0.1MSPE: 1.115 -> 0.487Improved
Use BAST instead of sparse inGP on bitten torusBAST · Bitten torus, sigma=0.1MAPE: 1.159 -> 0.307Improved
Use BAST instead of BART on real chlorophyll dataBAST · Aral chlorophyll dataMSPE: 2.933 -> 2.346Improved
Use BAST instead of BART on real chlorophyll dataBAST · Aral chlorophyll dataMean CRPS: 0.955 -> 0.633Improved
Use BAST instead of SFS on real chlorophyll dataBAST · Aral chlorophyll dataMAPE: 1.071 -> 0.905Improved
Increase number of weak learners in BARTBART · U-shape domainprediction errorNo clear effect
Fine-tune M, k-bar and shrinkage a for sigma_mu by cross-validation (ablation)BAST · U-shape domainprediction errorNo clear effect

Later papers that compared with this method

1 later accepted paper reports BAST as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy