Soft-BCT extends Bayesian context trees to real-valued time series with soft probabilistic splits learned via variational inference and shows better performance than prior hard-split BCT on some datasets.
Bayesian change-point detection via context-tree weighting,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Soft Bayesian Context Tree Models for Real-Valued Time Series
Soft-BCT extends Bayesian context trees to real-valued time series with soft probabilistic splits learned via variational inference and shows better performance than prior hard-split BCT on some datasets.