Structured learning modulo theories
From MaRDI portal
Abstract: Modelling problems containing a mixture of Boolean and numerical variables is a long-standing interest of Artificial Intelligence. However, performing inference and learning in hybrid domains is a particularly daunting task. The ability to model this kind of domains is crucial in "learning to design" tasks, that is, learning applications where the goal is to learn from examples how to perform automatic {em de novo} design of novel objects. In this paper we present Structured Learning Modulo Theories, a max-margin approach for learning in hybrid domains based on Satisfiability Modulo Theories, which allows to combine Boolean reasoning and optimization over continuous linear arithmetical constraints. The main idea is to leverage a state-of-the-art generalized Satisfiability Modulo Theory solver for implementing the inference and separation oracles of Structured Output SVMs. We validate our method on artificial and real world scenarios.
Recommendations
Cites work
- scientific article; zbMATH DE number 5296741 (Why is no real title available?)
- scientific article; zbMATH DE number 5263038 (Why is no real title available?)
- scientific article; zbMATH DE number 5493266 (Why is no real title available?)
- A Constraint Sequent Calculus for First-Order Logic with Linear Integer Arithmetic
- A hierarchy of relaxations for linear generalized disjunctive programming
- A modular approach to MaxSAT modulo theories
- Bridging logic and kernel machines
- Compiling constraints in clp(FD)
- Computing layouts with deformable templates
- Cutting-plane training of structural SVMs
- Disjunctive Programming
- Extending ProbLog with Continuous Distributions
- Inference in probabilistic logic programs with continuous random variables
- Large margin methods for structured and interdependent output variables
- Lazy satisfiability modulo theories
- Machine learning and knowledge discovery in databases. European conference, ECML PKDD 2011, Athens, Greece, September 5--9, 2011. Proceedings, Part II
- Minimal-model-guided approaches to solving polynomial constraints and extensions
- Mixed integer programming computation
- Model Evolution with Equality Modulo Built-in Theories
- On SAT Modulo Theories and Optimization Problems
- On probabilistic inference by weighted model counting
- Optimization in SMT with \(\mathcal{LA}(\mathbb Q)\) cost functions
- Optimization modulo theories with linear rational costs
- Propagation of Probabilities, Means, and Variances in Mixed Graphical Association Models
- Pushing the Envelope of Optimization Modulo Theories with Linear-Arithmetic Cost Functions
- Satisfiability modulo the theory of costs: foundations and applications
- Solving non-linear arithmetic
- Stochastic local search for SMT: combining theory solvers with WalkSAT
- Symbolic optimization with SMT solvers
- The magic of logical inference in probabilistic programming
Cited in
(9)- \textsc{OptiMathSAT}: a tool for optimization modulo theories
- Delegatable functional signatures
- Learning modulo theories for constructive preference elicitation
- Automatic synthesis of constraints from examples using mixed integer linear programming
- Learning Modulo Theories
- Ellipsoidal one-class constraint acquisition for quadratically constrained programming
- Learning relational dependency networks in hybrid domains
- Learning MAX-SAT from contextual examples for combinatorial optimisation
- Constraint learning: an appetizer
This page was built for publication: Structured learning modulo theories
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q511777)
