We study the problem of building generative models of natural source code (NSC); that is, source code written and understood by humans. Our primary contribution is to describe a family of generative models for NSC that have three key properties: First, they incorporate both sequential and hierarchical structure. Second, we learn a distributed representation of source code elements. Finally, they integrate closely with a compiler, which allows leveraging compiler logic and abstractions when building structure into the model. We also develop an extension that includes more complex structure, refining how the model generates identifier tokens based on what variables are currently in scope. Our models can be learned efficiently, and we show empirically that including appropriate structure greatly improves the models, measured by the probability of generating test programs.

Many scientific and engineering applications feature nonsmooth convex minimization problems over convex sets. In this paper, we address an important instance of this broad class where we assume that the nonsmooth objective is equipped with a tractable proximity operator and that the convex constraint set affords a self-concordant barrier. We provide a new joint treatment of proximal and self-concordant barrier concepts and illustrate that such problems can be efficiently solved, without the need of lifting the problem dimensions, as in disciplined convex optimization approach. We propose an inexact path-following algorithmic framework and theoretically characterize the worst-case analytical complexity of this framework when the proximal subproblems are solved inexactly. To show the merits of our framework, we apply its instances to both synthetic and real-world applications, where it shows advantages over standard interior point methods. As a by-product, we describe how our framework can obtain points on the Pareto frontier of regularized problems with self-concordant objectives in a tuning free fashion.

In this paper, we analyze different preconditionings designed to enhance robustness of pure-pixel search algorithms, which are used for blind hyperspectral unmixing and which are equivalent to near-separable nonnegative matrix factorization algorithms. Our analysis focuses on the successive projection algorithm (SPA), a simple, efficient and provably robust algorithm in the pure-pixel algorithm class. Recently, a provably robust preconditioning was proposed by Gillis and Vavasis (arXiv:1310.2273) which requires the resolution of a semidefinite program (SDP) to find a data points-enclosing minimum volume ellipsoid. Since solving the SDP in high precisions can be time consuming, we generalize the robustness analysis to approximate solutions of the SDP, that is, solutions whose objective function values are some multiplicative factors away from the optimal value. It is shown that a high accuracy solution is not crucial for robustness, which paves the way for faster preconditionings (e.g., based on first-order optimization methods). This first contribution also allows us to provide a robustness analysis for two other preconditionings. The first one is pre-whitening, which can be interpreted as an optimal solution of the same SDP with additional constraints. We analyze robustness of pre-whitening which allows us to characterize situations in which it performs competitively with the SDP-based preconditioning. The second one is based on SPA itself and can be interpreted as an optimal solution of a relaxation of the SDP. It is extremely fast while competing with the SDP-based preconditioning on several synthetic data sets.

Structured prediction is the problem of learning a function that maps structured inputs to structured outputs. Prototypical examples of structured prediction include part-of-speech tagging and semantic segmentation of images. Inspired by the recent successes of search-based structured prediction, we introduce a new framework for structured prediction called HC-Search. Given a structured input, the framework uses a search procedure guided by a learned heuristic H to uncover high quality candidate outputs and then employs a separate learned cost function C to select a final prediction among those outputs. The overall loss of this prediction architecture decomposes into the loss due to H not leading to high quality outputs, and the loss due to C not selecting the best among the generated outputs. Guided by this decomposition, we minimize the overall loss in a greedy stage-wise manner by first training H to quickly uncover high quality outputs via imitation learning, and then training C to correctly rank the outputs generated via H according to their true losses. Importantly, this training procedure is sensitive to the particular loss function of interest and the time-bound allowed for predictions. Experiments on several benchmark domains show that our approach significantly outperforms several state-of-the-art methods.

Monte Carlo Tree Search (MCTS) has improved the performance of game engines in domains such as Go, Hex, and general game playing. MCTS has been shown to outperform classic alpha-beta search in games where good heuristic evaluations are difficult to obtain. In recent years, combining ideas from traditional minimax search in MCTS has been shown to be advantageous in some domains, such as Lines of Action, Amazons, and Breakthrough. In this paper, we propose a new way to use heuristic evaluations to guide the MCTS search by storing the two sources of information, estimated win rates and heuristic evaluations, separately. Rather than using the heuristic evaluations to replace the playouts, our technique backs them up implicitly during the MCTS simulations. These minimax values are then used to guide future simulations. We show that using implicit minimax backups leads to stronger play performance in Kalah, Breakthrough, and Lines of Action.

Subsampling methods have been recently proposed to speed up least squares estimation in large scale settings. However, these algorithms are typically not robust to outliers or corruptions in the observed covariates. The concept of influence that was developed for regression diagnostics can be used to detect such corrupted observations as shown in this paper. This property of influence -- for which we also develop a randomized approximation -- motivates our proposed subsampling algorithm for large scale corrupted linear regression which limits the influence of data points since highly influential points contribute most to the residual error. Under a general model of corrupted observations, we show theoretically and empirically on a variety of simulated and real datasets that our algorithm improves over the current state-of-the-art approximation schemes for ordinary least squares.

In the past few years, a lot of attention has been devoted to multimedia indexing by fusing multimodal informations. Two kinds of fusion schemes are generally considered: The early fusion and the late fusion. We focus on late classifier fusion, where one combines the scores of each modality at the decision level. To tackle this problem, we investigate a recent and elegant well-founded quadratic program named MinCq coming from the machine learning PAC-Bayesian theory. MinCq looks for the weighted combination, over a set of real-valued functions seen as voters, leading to the lowest misclassification rate, while maximizing the voters' diversity. We propose an extension of MinCq tailored to multimedia indexing. Our method is based on an order-preserving pairwise loss adapted to ranking that allows us to improve Mean Averaged Precision measure while taking into account the diversity of the voters that we want to fuse. We provide evidence that this method is naturally adapted to late fusion procedures and confirm the good behavior of our approach on the challenging PASCAL VOC'07 benchmark.

These authors contributed equally to this work. The real surprise, however, is that even if one only has the ability to passively observe the early system, the quantum correlations hold signatures of the causal structure--in other words, certain types of correlation do imply causation. In a recent paper, Fitzsimons, Jones and Vedral [3] defined a function of the observed correlations which acts as a witness of direct causal influence, by ruling out a purely common-cause explanation. We here present the larger framework that places this result on an equal footing with an analogous result for common-cause relations. The problem of using observed correlations to infer causal relations is relevant to a wide variety of scientific disciplines. Yet given correlations between just two classical variables, it is impossible to determine whether they arose from a causal influence of one on the other or a common cause influencing both, unless one can implement a randomized intervention. We here consider the problem of causal inference for quantum variables. We introduce causal tomography, which unifies and generalizes conventional quantum tomography schemes to provide a complete solution to the causal inference problem using a quantum analogue of a randomized trial. We furthermore show that, in contrast to the classical case, observed quantum correlations alone can sometimes provide a solution. We implement a quantum-optical experiment that allows us to control the causal relation between two optical modes, and two measurement schemes--one with and one without randomization-- that extract this relation from the observed correlations.

We analyze variational inference for highly symmetric graphical models such as those arising from first-order probabilistic models. We first show that for these graphical models, the tree-reweighted variational objective lends itself to a compact lifted formulation which can be solved much more efficiently than the standard TRW formulation for the ground graphical model. Compared to earlier work on lifted belief propagation, our formulation leads to a convex optimization problem for lifted marginal inference and provides an upper bound on the partition function. We provide two approaches for improving the lifted TRW upper bound. The first is a method for efficiently computing maximum spanning trees in highly symmetric graphs, which can be used to optimize the TRW edge appearance probabilities. The second is a method for tightening the relaxation of the marginal polytope using lifted cycle inequalities and novel exchangeable cluster consistency constraints.

Property Directed Reachability (PDR) is a very promising recent method for deciding reachability in symbolically represented transition systems. While originally conceived as a model checking algorithm for hardware circuits, it has already been successfully applied in several other areas. This paper is the first investigation of PDR from the perspective of automated planning. Similarly to the planning as satisfiability paradigm, PDR draws its strength from internally employing an efficient SAT-solver. We show that most standard encoding schemes of planning into SAT can be directly used to turn PDR into a planning algorithm. As a non-obvious alternative, we propose to replace the SAT-solver inside PDR by a planning-specific procedure implementing the same interface. This SAT-solver free variant is not only more efficient, but offers additional insights and opportunities for further improvements. An experimental comparison to the state of the art planners finds it highly competitive, solving most problems on several domains.