We show new limits on the efficiency of using current techniques to make exact probabilistic inference for large classes of natural problems. In particular we show new lower bounds on knowledge compilation to SDD and DNNF forms. We give strong lower bounds on the complexity of SDD representations by relating SDD size to best-partition communication complexity. We use this relationship to prove exponential lower bounds on the SDD size for representing a large class of problems that occur naturally as queries over probabilistic databases. A consequence is that for representing unions of conjunctive queries, SDDs are not qualitatively more concise than OBDDs. We also derive simple examples for which SDDs must be exponentially less concise than FBDDs. Finally, we derive exponential lower bounds on the sizes of DNNF representations using a new quasipolynomial simulation of DNNFs by nondeterministic FBDDs.
Indian Institute of Technology Bombay(印度理工学院班加罗尔分校);University of Toronto(多伦多大学);Vector Institute(向量研究所);Georgia Institute of Technology(佐治亚理工学院);National University of Singapore(新加坡国立大学)
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University(符号计算与知识工程教育部重点实验室,吉林大学);School of Computing, National University of Singapore(新加坡国立大学计算学院)
On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results
Universidad Católica de Chile(智利天主教大学);IMFD Chile(智利数学与计算工程研究所);National Center for Artificial Intelligence, CENIA Chile(智利国家人工智能中心(CENIA));SKEMA Business School(SKEMA商学院);Univ. Lille(里尔大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Centrale Lille(里尔中央理工学院)
Solving Combinatorial Counting Problems with Weighted First-Order Model Counting
School of Artificial Intelligence, Jilin University, Changchun, China;State Key Laboratory of Complex \& Critical Software Environment, Beihang University, China;National Research Center for Educational Materials, China;Tengen Intelligence Institute, China;Czech Technical University in Prague, Prague, Czech Republic
Learning Branching Heuristics for Propositional Model Counting
University of Toronto(多伦多大学);UC Berkeley(加州大学伯克利分校);Vector Institute(向量研究所)
命题模型计数(Propositional Model Counting),或#SAT,是计算布尔公式的满意赋值的数量的问题。来自不同应用领域的许多问题,包括许多离散概率推理问题,可以转化为模型计数问题,由#SAT求解器来解决。然而,精确的#SAT求解器通常不能扩展到工业规模的实例。在本文中,我们提出了Neuro#,一种用于学习分支算法的方法,以提高给定问题族实例上的精确SAT求解器的性能。我们的实验表明,我们的方法减少了类似的分布式举行了实例的步骤数,并推广到更大的实例,从同一个问题的家庭。它是能够实现这些结果对一些不同的问题家庭具有非常不同的结构。除了步数改进之外,Neuro#还可以在某些问题族中的较大实例上实现比vanilla求解器高出几个数量级的挂钟加速,尽管查询模型的运行时开销很大。