Required sample size for learning sparse Bayesian networks with many variables
Pawel Wocjan, Dominik Janzing, Thomas Beth
Abstract
Learning joint probability distributions on n random variables requires exponential sample size in the generic case. Here we consider the case that a temporal (or causal) order of the variables is known and that the (unknown) graph of causal dependencies has bounded in-degree Delta. Then the joint measure is uniquely determined by the probabilities of all (2 Delta+1)-tuples. Upper bounds on the sample size required for estimating their probabilities can be given in terms of the VC-dimension of the set of corresponding cylinder sets. The sample size grows less than linearly with n.
Create a lesson
Related papers
Molecular Prior Networks
Pawel Gomoluch, Anthony Bradley
Dual-VaDE: Efficient and Robust Prototype Learning via Variational Dual-Domain Mixture Priors
Wugeng Zheng, Song Wang, Jian Wang
Effects of Parton Pair Correlations on Direct-Photon Yields and Elliptic Flow in Heavy-Ion Collisions
Xingjian Lu, Shuzhe Shi
Positional Encoding is All You Need for Scalable Equivariance Constraint Relaxation
Hagay Michaeli, Haggai Maron, Daniel Soudry
Federated Transfer Learning for Medical Image Classification under Mixed Skew
Alexandre G. Leclercq, Sébastien Bougleux, Aurélien Corroyer-Dulmont et al.
DRAP: Dynamics-Risk Adaptive Plasticity for Continual Learning in Physical AI
Oswaldo Ludwig