PyTorchKR Papers

최신 논문

총 3,318편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1504.05811

Learning of Behavior Trees for Autonomous Agents

Definition of an accurate system model for Automated Planner (AP) is often impractical, especially for real-world problems. Conversely, off-the-shelf planners fail to scale up and are domain dependent. These drawbacks are inherited from conventional transition systems such as Finite State Machines (FSMs) that describes the action-plan execution generated by the AP. On the other hand, Behavior Trees (BTs) represent a valid alternative to FSMs presenting many advantages in terms of modularity, reactiveness, scalability and domain-independence. In this paper, we propose a model-free AP framework using Genetic Programming (GP) to derive an optimal BT for an autonomous agent to achieve a given goal in unknown (but fully observable) environments. We illustrate the proposed framework using experiments conducted with an open source benchmark Mario AI for automated generation of BTs that can play the game character Mario to complete a certain level at various levels of difficulty to include enemies and obstacles.

arXiv:1505.00388

Order-Revealing Encryption and the Hardness of Private Learning

An order-revealing encryption scheme gives a public procedure by which two ciphertexts can be compared to reveal the ordering of their underlying plaintexts. We show how to use order-revealing encryption to separate computationally efficient PAC learning from efficient $(\epsilon, \delta)$-differentially private PAC learning. That is, we construct a concept class that is efficiently PAC learnable, but for which every efficient learner fails to be differentially private. This answers a question of Kasiviswanathan et al. (FOCS '08, SIAM J. Comput. '11). To prove our result, we give a generic transformation from an order-revealing encryption scheme into one with strongly correct comparison, which enables the consistent comparison of ciphertexts that are not obtained as the valid encryption of any message. We believe this construction may be of independent interest.

arXiv:1505.01072

Mining Measured Information from Text

We present an approach to extract measured information from text (e.g., a 1370 degrees C melting point, a BMI greater than 29.9 kg/m^2 ). Such extractions are critically important across a wide range of domains - especially those involving search and exploration of scientific and technical documents. We first propose a rule-based entity extractor to mine measured quantities (i.e., a numeric value paired with a measurement unit), which supports a vast and comprehensive set of both common and obscure measurement units. Our method is highly robust and can correctly recover valid measured quantities even when significant errors are introduced through the process of converting document formats like PDF to plain text. Next, we describe an approach to extracting the properties being measured (e.g., the property "pixel pitch" in the phrase "a pixel pitch as high as 352 {\mu}m"). Finally, we present MQSearch: the realization of a search engine with full support for measured information.

arXiv:1505.00869

On the Feasibility of Distributed Kernel Regression for Big Data

In modern scientific research, massive datasets with huge numbers of observations are frequently encountered. To facilitate the computational process, a divide-and-conquer scheme is often used for the analysis of big data. In such a strategy, a full dataset is first split into several manageable segments; the final output is then averaged from the individual outputs of the segments. Despite its popularity in practice, it remains largely unknown that whether such a distributive strategy provides valid theoretical inferences to the original data. In this paper, we address this fundamental issue for the distributed kernel regression (DKR), where the algorithmic feasibility is measured by the generalization performance of the resulting estimator. To justify DKR, a uniform convergence rate is needed for bounding the generalization error over the individual outputs, which brings new and challenging issues in the big data setup. Under mild conditions, we show that, with a proper number of segments, DKR leads to an estimator that is generalization consistent to the unknown regression function. The obtained results justify the method of DKR and shed light on the feasibility of using other distributed algorithms for processing big data. The promising preference of the method is supported by both simulation and real data examples.

arXiv:1501.04053

Stochastic Local Interaction (SLI) Model: Interfacing Machine Learning and Geostatistics

Machine learning and geostatistics are powerful mathematical frameworks for modeling spatial data. Both approaches, however, suffer from poor scaling of the required computational resources for large data applications. We present the Stochastic Local Interaction (SLI) model, which employs a local representation to improve computational efficiency. SLI combines geostatistics and machine learning with ideas from statistical physics and computational geometry. It is based on a joint probability density function defined by an energy functional which involves local interactions implemented by means of kernel functions with adaptive local kernel bandwidths. SLI is expressed in terms of an explicit, typically sparse, precision (inverse covariance) matrix. This representation leads to a semi-analytical expression for interpolation (prediction), which is valid in any number of dimensions and avoids the computationally costly covariance matrix inversion.

arXiv:1507.00039

Selective Inference and Learning Mixed Graphical Models

This thesis studies two problems in modern statistics. First, we study selective inference, or inference for hypothesis that are chosen after looking at the data. The motiving application is inference for regression coefficients selected by the lasso. We present the Condition-on-Selection method that allows for valid selective inference, and study its application to the lasso, and several other selection algorithms. In the second part, we consider the problem of learning the structure of a pairwise graphical model over continuous and discrete variables. We present a new pairwise model for graphical models with both continuous and discrete variables that is amenable to structure learning. In previous work, authors have considered structure learning of Gaussian graphical models and structure learning of discrete models. Our approach is a natural generalization of these two lines of work to the mixed case. The penalization scheme involves a novel symmetric use of the group-lasso norm and follows naturally from a particular parametrization of the model. We provide conditions under which our estimator is model selection consistent in the high-dimensional regime.

arXiv:1505.06651

A Logic of Knowing How

In this paper, we propose a single-agent modal logic framework for reasoning about goal-direct "knowing how" based on ideas from linguistics, philosophy, modal logic and automated planning. We first define a modal language to express "I know how to guarantee phi given psi" with a semantics not based on standard epistemic models but labelled transition systems that represent the agent's knowledge of his own abilities. A sound and complete proof system is given to capture the valid reasoning patterns about "knowing how" where the most important axiom suggests its compositional nature.

arXiv:1505.06163

Direct Variational Perspective Shape from Shading with Cartesian Depth Parametrisation

Most of today's state-of-the-art methods for perspective shape from shading are modelled in terms of partial differential equations (PDEs) of Hamilton-Jacobi type. To improve the robustness of such methods w.r.t. noise and missing data, first approaches have recently been proposed that seek to embed the underlying PDE into a variational framework with data and smoothness term. So far, however, such methods either make use of a radial depth parametrisation that makes the regularisation hard to interpret from a geometrical viewpoint or they consider indirect smoothness terms that require additional consistency constraints to provide valid solutions. Moreover the minimisation of such frameworks is an intricate task, since the underlying energy is typically non-convex. In our paper we address all three of the aforementioned issues. First, we propose a novel variational model that operates directly on the Cartesian depth. In this context, we also point out a common mistake in the derivation of the surface normal. Moreover, we employ a direct second-order regulariser with edge-preservation property. This direct regulariser yields by construction valid solutions without requiring additional consistency constraints. Finally, we also propose a novel coarse-to-fine minimisation framework based on an alternating explicit scheme. This framework allows us to avoid local minima during the minimisation and thus to improve the accuracy of the reconstruction. Experiments show the good quality of our model as well as the usefulness of the proposed numerical scheme.

arXiv:1407.8322

Zipf's law for word frequencies: word forms versus lemmas in long texts

Zipf's law is a fundamental paradigm in the statistics of written and spoken natural language as well as in other communication systems. We raise the question of the elementary units for which Zipf's law should hold in the most natural way, studying its validity for plain word forms and for the corresponding lemma forms. In order to have as homogeneous sources as possible, we analyze some of the longest literary texts ever written, comprising four different languages, with different levels of morphological complexity. In all cases Zipf's law is fulfilled, in the sense that a power-law distribution of word or lemma frequencies is valid for several orders of magnitude. We investigate the extent to which the word-lemma transformation preserves two parameters of Zipf's law: the exponent and the low-frequency cut-off. We are not able to demonstrate a strict invariance of the tail, as for a few texts both exponents deviate significantly, but we conclude that the exponents are very similar, despite the remarkable transformation that going from words to lemmas represents, considerably affecting all ranges of frequencies. In contrast, the low-frequency cut-offs are less stable.

arXiv:1507.04761

Deep Learning and Music Adversaries

An adversary is essentially an algorithm intent on making a classification system perform in some particular way given an input, e.g., increase the probability of a false negative. Recent work builds adversaries for deep learning systems applied to image object recognition, which exploits the parameters of the system to find the minimal perturbation of the input image such that the network misclassifies it with high confidence. We adapt this approach to construct and deploy an adversary of deep learning systems applied to music content analysis. In our case, however, the input to the systems is magnitude spectral frames, which requires special care in order to produce valid input audio signals from network-derived perturbations. For two different train-test partitionings of two benchmark datasets, and two different deep architectures, we find that this adversary is very effective in defeating the resulting systems. We find the convolutional networks are more robust, however, compared with systems based on a majority vote over individually classified audio frames. Furthermore, we integrate the adversary into the training of new deep systems, but do not find that this improves their resilience against the same adversary.

arXiv:1507.08711

Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs

State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution. Here, we propose to go beyond these representations and model image-sets as probability distribution functions (PDFs) using kernel density estimators. To compare and match image-sets, we exploit Csiszar f-divergences, which bear strong connections to the geodesic distance defined on the space of PDFs, i.e., the statistical manifold. Furthermore, we introduce valid positive definite kernels on the statistical manifolds, which let us make use of more powerful classification schemes to match image-sets. Finally, we introduce a supervised dimensionality reduction technique that learns a latent space where f-divergences reflect the class labels of the data. Our experiments on diverse problems, such as video-based face recognition and dynamic texture classification, evidence the benefits of our approach over the state-of-the-art image-set matching methods.

arXiv:1508.01340

Universal Approximation of Edge Density in Large Graphs

In this paper, we present a novel way to summarize the structure of large graphs, based on non-parametric estimation of edge density in directed multigraphs. Following coclustering approach, we use a clustering of the vertices, with a piecewise constant estimation of the density of the edges across the clusters, and address the problem of automatically and reliably inferring the number of clusters, which is the granularity of the coclustering. We use a model selection technique with data-dependent prior and obtain an exact evaluation criterion for the posterior probability of edge density estimation models. We demonstrate, both theoretically and empirically, that our data-dependent modeling technique is consistent, resilient to noise, valid non asymptotically and asymptotically behaves as an universal approximator of the true edge density in directed multigraphs. We evaluate our method using artificial graphs and present its practical interest on real world graphs. The method is both robust and scalable. It is able to extract insightful patterns in the unsupervised learning setting and to provide state of the art accuracy when used as a preparation step for supervised learning.

arXiv:1502.03655공식 코드 · Papers with Code

Newton-based maximum likelihood estimation in nonlinear state space models

Maximum likelihood (ML) estimation using Newton's method in nonlinear state space models (SSMs) is a challenging problem due to the analytical intractability of the log-likelihood and its gradient and Hessian. We estimate the gradient and Hessian using Fisher's identity in combination with a smoothing algorithm. We explore two approximations of the log-likelihood and of the solution of the smoothing problem. The first is a linearization approximation which is computationally cheap, but the accuracy typically varies between models. The second is a sampling approximation which is asymptotically valid for any SSM but is more computationally costly. We demonstrate our approach for ML parameter estimation on simulated data from two different SSMs with encouraging results.

arXiv:1510.02442

Uniform Learning in a Deep Neural Network via "Oddball" Stochastic Gradient Descent

When training deep neural networks, it is typically assumed that the training examples are uniformly difficult to learn. Or, to restate, it is assumed that the training error will be uniformly distributed across the training examples. Based on these assumptions, each training example is used an equal number of times. However, this assumption may not be valid in many cases. "Oddball SGD" (novelty-driven stochastic gradient descent) was recently introduced to drive training probabilistically according to the error distribution - training frequency is proportional to training error magnitude. In this article, using a deep neural network to encode a video, we show that oddball SGD can be used to enforce uniform error across the training set.

arXiv:1510.01518

DC Decomposition of Nonconvex Polynomials with Algebraic Techniques

We consider the problem of decomposing a multivariate polynomial as the difference of two convex polynomials. We introduce algebraic techniques which reduce this task to linear, second order cone, and semidefinite programming. This allows us to optimize over subsets of valid difference of convex decompositions (dcds) and find ones that speed up the convex-concave procedure (CCP). We prove, however, that optimizing over the entire set of dcds is NP-hard.

arXiv:1508.00144

Quantitative evaluation of the performance of discrete-time reservoir computers in the forecasting, filtering, and reconstruction of stochastic stationary signals

This paper extends the notion of information processing capacity for non-independent input signals in the context of reservoir computing (RC). The presence of input autocorrelation makes worthwhile the treatment of forecasting and filtering problems for which we explicitly compute this generalized capacity as a function of the reservoir parameter values using a streamlined model. The reservoir model leading to these developments is used to show that, whenever that approximation is valid, this computational paradigm satisfies the so called separation and fading memory properties that are usually associated with good information processing performances. We show that several standard memory, forecasting, and filtering problems that appear in the parametric stochastic time series context can be readily formulated and tackled via RC which, as we show, significantly outperforms standard techniques in some instances.

arXiv:1510.08039

Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties

Model-based approaches to 3D hand tracking have been shown to perform well in a wide range of scenarios. However, they require initialisation and cannot recover easily from tracking failures that occur due to fast hand motions. Data-driven approaches, on the other hand, can quickly deliver a solution, but the results often suffer from lower accuracy or missing anatomical validity compared to those obtained from model-based approaches. In this work we propose a hybrid approach for hand pose estimation from a single depth image. First, a learned regressor is employed to deliver multiple initial hypotheses for the 3D position of each hand joint. Subsequently, the kinematic parameters of a 3D hand model are found by deliberately exploiting the inherent uncertainty of the inferred joint proposals. This way, the method provides anatomically valid and accurate solutions without requiring manual initialisation or suffering from track losses. Quantitative results on several standard datasets demonstrate that the proposed method outperforms state-of-the-art representatives of the model-based, data-driven and hybrid paradigms.

arXiv:1510.07905

Defect Detection Techniques for Airbag Production Sewing Stages

Airbags are subject to strict quality control in order to ensure passengers safety. The quality of fabric and sewing thread influence the final product and therefore, sewing defects must be early and accurately detected, in order to remove the item from production. Airbag seams assembly can take various forms, using linear and circle primitives, with threads of different colors and length densities, creating lockstitch or double threads chainstitch. The paper presents a framework for the automatic detection of defects occurring during the airbag sewing stage. Types of defects as skipped stitch, missed stitch or superimposed seam for lockstitch and two threads chainstitch are detected and marked. Using image processing methods, the proposed framework follows the seams path and determines if a color pattern of the considered stitches is valid.

arXiv:1511.01512

Mean-field inference of Hawkes point processes

We propose a fast and efficient estimation method that is able to accurately recover the parameters of a d-dimensional Hawkes point-process from a set of observations. We exploit a mean-field approximation that is valid when the fluctuations of the stochastic intensity are small. We show that this is notably the case in situations when interactions are sufficiently weak, when the dimension of the system is high or when the fluctuations are self-averaging due to the large number of past events they involve. In such a regime the estimation of a Hawkes process can be mapped on a least-squares problem for which we provide an analytic solution. Though this estimator is biased, we show that its precision can be comparable to the one of the Maximum Likelihood Estimator while its computation speed is shown to be improved considerably. We give a theoretical control on the accuracy of our new approach and illustrate its efficiency using synthetic datasets, in order to assess the statistical estimation error of the parameters.

arXiv:1502.06800

On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions

We show that kernel-based quadrature rules for computing integrals can be seen as a special case of random feature expansions for positive definite kernels, for a particular decomposition that always exists for such kernels. We provide a theoretical analysis of the number of required samples for a given approximation error, leading to both upper and lower bounds that are based solely on the eigenvalues of the associated integral operator and match up to logarithmic terms. In particular, we show that the upper bound may be obtained from independent and identically distributed samples from a specific non-uniform distribution, while the lower bound if valid for any set of points. Applying our results to kernel-based quadrature, while our results are fairly general, we recover known upper and lower bounds for the special cases of Sobolev spaces. Moreover, our results extend to the more general problem of full function approximations (beyond simply computing an integral), with results in L2- and L$\infty$-norm that match known results for special cases. Applying our results to random features, we show an improvement of the number of random features needed to preserve the generalization guarantees for learning with Lipschitz-continuous losses.