In the last few years the systematic adoption of deep learning to visual generation has produced impressive results that, amongst others, definitely benefit from the massive exploration of convolutional architectures. In this paper, we propose a general approach to visual generation that combines learning capabilities with logic descriptions of the target to be generated. The process of generation is regarded as a constrained satisfaction problem, where the constraints describe a set of properties that characterize the target. Interestingly, the constraints can also involve logic variables, while all of them are converted into real-valued functions by means of the t-norm theory. We use deep architectures to model the involved variables, and propose a computational scheme where the learning process carries out a satisfaction of the constraints. We propose some examples in which the theory can naturally be used, including the modeling of GAN and auto-encoders, and report promising results in problems with the generation of handwritten characters and face transformations.

Factored stochastic constraint programming (FSCP) is a formalism to represent multi-stage decision making problems under uncertainty. FSCP models support factorized probabilistic models and involve constraints over decision and random variables. These models have many applications in real-world problems. However, solving these problems requires evaluating the best course of action for each possible outcome of the random variables and hence is computationally challenging. FSCP problems often involve repeated subproblems which ideally should be solved once. In this paper we show how identifying and exploiting these identical subproblems can simplify solving them and leads to a compact representation of the solution. We compile an And-Or search tree to a compact decision diagram. Preliminary experiments show that our proposed method significantly improves the search efficiency by reducing the size of the problem and outperforms the existing methods.

The focus of my PhD thesis is on exploring parallel approaches to efficiently solve problems modeled by constraints and presenting a new proposal. Current solvers are very advanced; they are carefully designed to effectively manage the high-level problems' description and include refined strategies to avoid useless work. Despite this, finding a solution can take an unacceptable amount of time. Parallelization can mitigate this problem when the instance of the problem modeled is large, as it happens in real world problems. It is done by propagating constraints in parallel and concurrently exploring different parts of the search space. I am developing on a constraint solver that exploits the many cores available on Graphics Processing Units (GPU) to speed up the search.

In this work, we present a novel human-in-the-loop framework to help the human user understand the decision making process that involves choosing preferred options. We focus on qualitative preference models over alternatives from combinatorial domains. This framework is interactive: the user provides her behavioral data to the framework, and the framework explains the learned model to the user. It is iterative: the framework collects feedback on the learned model from the user and tries to improve it accordingly till the user terminates the iteration. In order to communicate the learned preference model to the user, we develop visualization of intuitive and explainable graphic models, such as lexicographic preference trees and forests, and conditional preference networks. To this end, we discuss key aspects of our framework for lexicographic preference models.

Constraint satisfaction problems form an important and wide class of combinatorial search and optimization problems with many applications in AI and other areas. We introduce a recurrent neural network architecture RUN-CSP (Recurrent Unsupervised Neural Network for Constraint Satisfaction Problems) to train message passing networks solving binary constraint satisfaction problems (CSPs) or their optimization versions (Max-CSP). The architecture is universal in the sense that it works for all binary CSPs: depending on the constraint language, we can automtically design a loss function, which is then used to train generic neural nets. In this paper, we experimentally evaluate our approach for the 3-colorability problem (3-Col) and its optimization version (Max-3-Col) and for the maximum 2-satisfiability problem (Max-2-Sat). We also extend the framework to work for related optimization problems such as the maximum independent set problem (Max-IS). Training is unsupervised, we train the network on arbitrary (unlabeled) instances of the problems. Moreover, we experimentally show that it suffices to train on relatively small instances; the resulting message passing network will perform well on much larger instances (at least 10-times larger).

In this thesis, we introduce a novel formal framework to represent and reason about qualitative direction and distance relations between extended objects using Answer Set Programming (ASP). We take Cardinal Directional Calculus (CDC) as a starting point and extend CDC with new sorts of constraints which involve defaults, preferences and negation. We call this extended version as nCDC. Then we further extend nCDC by augmenting qualitative distance relation and name this extension as nCDC+. For CDC, nCDC, nCDC+, we introduce an ASP-based general framework to solve consistency checking problems, address composition and inversion of qualitative spatial relations, infer unknown or missing relations between objects, and find a suitable configuration of objects which fulfills a given inquiry.

The job-shop scheduling is one of the most studied optimization problems from the dawn of computer era to the present day. Its combinatorial nature makes it easily expressible as a constraint satisfaction problem. In this paper, we compare the performance of two constraint solvers on the job-shop scheduling problem. The solvers in question are: OR-Tools, an open-source solver developed by Google and winner of the last MiniZinc Challenge, and CP Optimizer, a proprietary IBM constraint solver targeted at industrial scheduling problems. The comparison is based on the goodness of the solutions found and the time required to solve the problem instances. First, we target the classic benchmarks from the literature, then we carry out the comparison on a benchmark that was created with known optimal solution, with size comparable to real-world industrial problems.

Barichard & I. St ephan This work is licensed under the Creative Commons Attribution License. Quantified Constraint Handling Rules Vincent Barichard LERIA, University of Angers Angers, France vincent.barichard@univ-angers.fr Igor St ephan LERIA, University of Angers Angers, France igor.stephan@univ-angers.fr We shift the QCSP (Quantified Constraint Satisfaction Problems) framework to the QCHR (Quantified Constraint Handling Rules) framework by enabling dynamic binder and access to user-defined constraints. QCSP offers a natural framework to express PSP ACE problems as finite two-players games. But to define a QCSP model, the binder must be formerly known and cannot be built dynamically even if the worst case won't occur. To overcome this issue, we define the new QCHR formalism that allows to build the binder dynamically during the solving. Our QCHR models exhibit state-of-the-art performances on static binder and outperforms previous QCSP approaches when the binder is dynamic. 1 Introduction We shift the QCSP (for Quantified Constraint Satisfaction Problems) framework to the QCHR (for Quantified Constraint Handling Rule) framework. Such shift is motivated by the difficulties for developing real applications in QCSP . QCSP [7, 26, 15, 4, 22, 20, 3] are a generalization of Constraint Satisfaction Problems (CSP) in which variables may be quantified existentially (as in CSP) and universally. A QCSP is an alternation of existentially and universally quantified variables over finite domains, the binder, followed by a CSP . Universally quantified variables represent uncontrollable parameters such as meteorological events.

We investigate conjunctive normal form (CNF) encodings of a function represented with a smooth decomposable negation normal form (DNNF). Several encodings of DNNFs and decision diagrams were considered by (Abio et al. 2016). The authors differentiate between encodings which implement consistency or domain consistency from encodings which implement unit refutation completeness or propagation completeness (in both cases implements means by unit propagation). The difference is that in the former case we do not care about properties of the encoding with respect to the auxiliary variables while in the latter case we treat all variables (the input ones and the auxiliary ones) in the same way. The latter case is useful if a DNNF is a part of a problem containing also other constraints and a SAT solver is used to test satisfiability. The currently known encodings of smooth DNNF theories implement domain consistency. Building on this and the result of (Abio et al. 2016) on an encoding of decision diagrams which implements propagation completeness, we present a new encoding of a smooth DNNF which implements propagation completeness. This closes the gap left open in the literature on encodings of DNNFs.

Distributed Pseudo-tree Optimization Procedure (DPOP) is a well-known message passing algorithm that has been used to provide optimal solutions of Distributed Constraint Optimization Problems (DCOPs) -- a framework that is designed to optimize constraints in cooperative multi-agent systems. The traditional DCOP formulation does not consider those constraints that must be satisfied (also known as hard constraints), rather it concentrates only on soft constraints. However, the presence of both types of constraints are observed in a number of applications, such as Distributed Radio Link Frequency Assignment and Distributed Event Scheduling, etc. Although the combination of these types of constraints is recently incorporated in DPOP to solve DCOPs, scalability remains an issue for them as finding an optimal solution is NP-hard. Additionally, in DPOP, the agents are arranged as a DFS pseudo-tree. Recently it has been observed that the constructed pseudo-trees in this way often come to be chain-like and greatly impair the algorithm's performance. To address these issues, we develop an algorithm that speeds up the DPOP algorithm by reducing the size of the messages exchanged and increasing parallelism in the pseudo tree. Our empirical evidence suggests that our approach outperforms the state-of-the-art algorithms by a significant margin.