Partition Function Estimation: A Quantitative Study

@inproceedings{Agrawal2021PartitionFE,
  title={Partition Function Estimation: A Quantitative Study},
  author={Durgesh Kumar Agrawal and Yash Pote and Kuldeep S. Meel},
  booktitle={IJCAI},
  year={2021}
}
Probabilistic graphical models have emerged as a powerful modeling tool for several real-world scenarios where one needs to reason under uncertainty. A graphical model’s partition function is a central quantity of interest, and its computation is key to several probabilistic reasoning tasks. Given the #Phardness of computing the partition function, several techniques have been proposed over the years with varying guarantees on the quality of estimates and their runtime behavior. This paper… 
View PDF on arXiv
View With Semantic Reader
4 Citations
Background Citations
1
Methods Citations
3

Figures and Tables from this paper

4 Citations

Causal Inference Using Tractable Circuits
TLDR
It is shown that probabilistic inference in the presence of (unknown) causal mechanisms can be tractable for models that have traditionally been viewed as intractable, enabled by a new technique that can exploit causal mechanisms computationally but without needing to know their identities.
Projected Model Counting: Beyond Independent Support
TLDR
This paper shows that contrary to intuition, it can be beneficial to project on variables beyond the projection set, and finds that UBS-based projected counting can solve many problem instances that are beyond the reach of a state-ofthe-art independent support- based projected model counter.
IBIA: Bayesian Inference via Incremental Build-Infer-Approximate operations on Clique Trees
TLDR
The algorithm for incremental construction of clique trees always generates a valid CT and the approximation technique automatically maintains consistency of within-clique beliefs, and the results show a significant reduction in error when compared to other approximate methods, with competitive runtimes.
Tractable Boolean and Arithmetic Circuits
  • Adnan Darwiche
  • Computer Science
    Neuro-Symbolic Artificial Intelligence
  • 2021
TLDR
This chapter reviews the foundations of tractable circuits and some associated milestones, while focusing on their core properties and techniques that make them particularly useful for the broad aims of neuro-symbolic AI.

References

SHOWING 1-10 OF 112 REFERENCES
Estimating the Partition Function of Graphical Models Using Langevin Importance Sampling
TLDR
A new Langevin Importance Sampling (LIS) algorithm is presented, which performs a random walk in the conguration-temp erature space guided by the Langevin equation and estimates the partition function using all the samples generated during the random walk at all the temperatures.
Dynamic Importance Sampling for Anytime Bounds of the Partition Function
TLDR
This paper constructs an unbiased estimator of the partition function with strong finite-sample confidence intervals that gives significantly improved anytime behavior, and more flexible trade-offs between memory, time, and solution quality.
A Weighted Mini-Bucket Bound for Solving Influence Diagram
TLDR
A weighted mini-bucket approach for bounding the maximum expected utility and its maximizing policy is developed, demonstrating its potential and evaluating the scheme empirically against the current state of the art.
Exact or approximate inference in graphical models: why the choice is dictated by the treewidth, and how variable elimination can be exploited
Probabilistic graphical models offer a powerful framework to account for the dependence structure between variables, which is represented as a graph. However, the dependence between variables may…
SampleSearch: Importance sampling in presence of determinism
Efficient semidefinite-programming-based inference for binary and multi-class MRFs
TLDR
An efficient method for computing the partition function or MAP estimate in a pairwise MRF by instead exploiting a recently proposed coordinate-descent-based fast semidefinite solver is proposed and substantially outperforms the existing state of the art in approximate inference.
GANAK: A Scalable Probabilistic Exact Model Counter
TLDR
GANAK is developed, a new scalable probabilistic exact model counter that outperforms state-of-the-art exact and approximate model counters sharpSAT and ApproxMC3 respectively, both in terms of PAR-2 score and the number of instances solved.
Taming Discrete Integration via the Boon of Dimensionality
TLDR
The proposed reduction is achieved via a significant increase in the dimensionality that leads to solving an instance of the relatively simpler problem of model counting, and is the first technique to compute estimates with provable guarantees for this class of benchmarks.
Flexible Approximate Inference via Stratified Normalizing Flows
TLDR
An approximate inference procedure is developed that allows explicit control of the bias/variance tradeoff, interpolating between the sampling and the variational regime, and uses a normalizing flow to map the integrand onto a uniform distribution.
Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations
TLDR
This work proposes the first approximate WMI solver that does not resort to sampling, but performs exact inference on an approximate model and iteratively performs message passing in a relaxed problem structure to recover lost dependencies.
...
...