The need to understand the inner workings of opaque Machine Learning models has prompted researchers to devise various types of post-hoc explanations. A large class of such explainers proceed in two phases: first perturb an input instance whose explanation is sought, and then generate an interpretable artifact to explain the prediction of the opaque model on that instance. Recently, Deutch and Frost proposed to use an additional input from the user: a set of constraints over the input space to guide the perturbation phase. While this approach affords the user the ability to tailor the explanation to their needs, striking a balance between flexibility, theoretical rigor and computational cost has remained an open challenge. We propose a novel constraint-driven explanation generation approach which simultaneously addresses these issues in a modular fashion. Our framework supports the use of expressive Boolean constraints giving the user more flexibility to specify the subspace to generate perturbations from. Leveraging advances in Formal Methods, we can theoretically guarantee strict adherence of the samples to the desired distribution. This also allows us to compute fidelity in a rigorous way, while scaling much better in practice. Our empirical study demonstrates concrete uses of our tool CLIME in obtaining more meaningful explanations with high fidelity.

The problem of exact weighted sampling of solutions of Boolean formulas has applications in Bayesian inference, testing, and verification. The state-of-the-art approach to sampling involves carefully decomposing the input formula and compiling a data structure called d-DNNF in the process. Recent work in the closely connected field of model counting, however, has shown that smartly composing different subformulas using dynamic programming and Algebraic Decision Diagrams (ADDs) can outperform d-DNNF-style approaches on many benchmarks. In this work, we present a modular algorithm called DPSampler that extends such dynamic-programming techniques to the problem of exact weighted sampling. DPSampler operates in three phases. First, an execution plan in the form of a project-join tree is computed using tree decompositions. Second, the plan is used to compile the input formula into a succinct tree-of-ADDs representation. Third, this tree is traversed to generate a random sample. This decoupling of planning, compilation and sampling phases enables usage of specialized libraries for each purpose in a black-box fashion. Further, our novel ADD-sampling algorithm avoids the need for expensive dynamic memory allocation required in previous work. Extensive experiments over diverse sets of benchmarks show DPSampler is more scalable and versatile than existing approaches.

A key problem in constrained random verification (CRV) concerns generation of input stimuli that result in good coverage of the system's runs in targeted corners of its behavior space. Existing CRV solutions however provide no formal guarantees on the distribution of the system's runs. In this paper, we take a first step towards solving this problem. We present an algorithm based on Algebraic Decision Diagrams for sampling bounded traces (i.e. sequences of states) of a sequential circuit with provable uniformity (or bias) guarantees, while satisfying given constraints. We have implemented our algorithm in a tool called TraceSampler. Extensive experiments show that TraceSampler outperforms alternative approaches that provide similar uniformity guarantees.

The problem of counting the number of solutions of a DNF formula, also called #DNF, is a fundamental problem in AI with wide-ranging applications. Owing to the intractability of the exact variant, efforts have focused on the design of approximate techniques. Consequently, several Fully Polynomial Randomized Approximation Schemes (FPRASs) based on Monte Carlo techniques have been proposed. Recently, it was discovered that hashing-based techniques too lend themselves to FPRASs for #DNF. Despite significant improvements, the complexity of the hashing-based FPRAS is still worse than that of the best Monte Carlo FPRAS by polylog factors. Two questions were left unanswered in previous works: Can the complexity of the hashing-based techniques be improved? How do these approaches compare empirically? In this paper, we first propose a new search procedure for the hashing-based FPRAS that removes the polylog factors from its time complexity. We then present the first empirical study of runtime behavior of different FPRASs for #DNF, which produces a nuanced picture. We observe that there is no single best algorithm for all formulas and that the algorithm with one of the worst time complexities solves the largest number of benchmarks.

Propositional model counting is a fundamental problem in artificial intelligence with a wide variety of applications, such as probabilistic inference, decision making under uncertainty, and probabilistic databases. Consequently, the problem is of theoretical as well as practical interest. When the constraints are expressed as DNF formulas, Monte Carlo-based techniques have been shown to provide a fully polynomial randomized approximation scheme (FPRAS). For CNF constraints, hashing-based approximation techniques have been demonstrated to be highly successful. Furthermore, it was shown that hashing-based techniques also yield an FPRAS for DNF counting without usage of Monte Carlo sampling. Our analysis, however, shows that the proposed hashing-based approach to DNF counting provides poor time complexity compared to the Monte Carlo-based DNF counting techniques. Given the success of hashing-based techniques for CNF constraints, it is natural to ask: Can hashing-based techniques provide an efficient FPRAS for DNF counting? In this paper, we provide a positive answer to this question. To this end, we introduce two novel algorithmic techniques: Symbolic Hashing and Stochastic Cell Counting, along with a new hash family of Row-Echelon hash functions. These innovations allow us to design a hashing-based FPRAS for DNF counting of similar complexity (up to polylog factors) as that of prior works. Furthermore, we expect these techniques to have potential applications beyond DNF counting.