PyTorchKR Papers

최신 논문

총 1,463편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1903.09115

Closed-Form Optimal Two-View Triangulation Based on Angular Errors

In this paper, we study closed-form optimal solutions to two-view triangulation with known internal calibration and pose. By formulating the triangulation problem as $L_1$ and $L_\infty$ minimization of angular reprojection errors, we derive the exact closed-form solutions that guarantee global optimality under respective cost functions. To the best of our knowledge, we are the first to present such solutions. Since the angular error is rotationally invariant, our solutions can be applied for any type of central cameras, be it perspective, fisheye or omnidirectional. Our methods also require significantly less computation than the existing optimal methods. Experimental results on synthetic and real datasets validate our theoretical derivations.

arXiv:1903.08432

Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks

Data-driven design approaches based on deep-learning have been introduced in nanophotonics to reduce time-consuming iterative simulations which have been a major challenge. Here, we report the first use of conditional deep convolutional generative adversarial networks to design nanophotonic antennae that are not constrained to a predefined shape. For given input reflection spectra, the network generates desirable designs in the form of images; this form allows suggestions of new structures that cannot be represented by structural parameters. Simulation results obtained from the generated designs agreed well with the input reflection spectrum. This method opens new avenues towards the development of nanophotonics by providing a fast and convenient approach to design complex nanophotonic structures that have desired optical properties.

arXiv:1903.08011

Data-driven PDE discovery with evolutionary approach

The data-driven models allow one to define the model structure in cases when a priori information is not sufficient to build other types of models. The possible way to obtain physical interpretation is the data-driven differential equation discovery techniques. The existing methods of PDE (partial derivative equations) discovery are bound with the sparse regression. However, sparse regression is restricting the resulting model form, since the terms for PDE are defined before regression. The evolutionary approach described in the article has a symbolic regression as the background instead and thus has fewer restrictions on the PDE form. The evolutionary method of PDE discovery (EPDE) is described and tested on several canonical PDEs. The question of robustness is examined on a noised data example.

arXiv:1903.05818

On power chi expansions of $f$-divergences

We consider both finite and infinite power chi expansions of $f$-divergences derived from Taylor's expansions of smooth generators, and elaborate on cases where these expansions yield closed-form formula, bounded approximations, or analytic divergence series expressions of $f$-divergences.

arXiv:1903.02675

A Rank-1 Sketch for Matrix Multiplicative Weights

We show that a simple randomized sketch of the matrix multiplicative weight (MMW) update enjoys (in expectation) the same regret bounds as MMW, up to a small constant factor. Unlike MMW, where every step requires full matrix exponentiation, our steps require only a single product of the form $e^A b$, which the Lanczos method approximates efficiently. Our key technique is to view the sketch as a $\textit{randomized mirror projection}$, and perform mirror descent analysis on the $\textit{expected projection}$. Our sketch solves the online eigenvector problem, improving the best known complexity bounds by $\Omega(\log^5 n)$. We also apply this sketch to semidefinite programming in saddle-point form, yielding a simple primal-dual scheme with guarantees matching the best in the literature.

arXiv:1903.00843

Multiple Learning for Regression in big data

Regression problems that have closed-form solutions are well understood and can be easily implemented when the dataset is small enough to be all loaded into the RAM. Challenges arise when data is too big to be stored in RAM to compute the closed form solutions. Many techniques were proposed to overcome or alleviate the memory barrier problem but the solutions are often local optimal. In addition, most approaches require accessing the raw data again when updating the models. Parallel computing clusters are also expected if multiple models need to be computed simultaneously. We propose multiple learning approaches that utilize an array of sufficient statistics (SS) to address this big data challenge. This memory oblivious approach breaks the memory barrier when computing regressions with closed-form solutions, including but not limited to linear regression, weighted linear regression, linear regression with Box-Cox transformation (Box-Cox regression) and ridge regression models. The computation and update of the SS array can be handled at per row level or per mini-batch level. And updating a model is as easy as matrix addition and subtraction. Furthermore, multiple SS arrays for different models can be easily computed simultaneously to obtain multiple models at one pass through the dataset. We implemented our approaches on Spark and evaluated over the simulated datasets. Results showed our approaches can achieve closed-form solutions of multiple models at the cost of half training time of the traditional methods for a single model.

arXiv:1902.10173

Online Learning with Continuous Ranked Probability Score

Probabilistic forecasts in the form of probability distributions over future events have become popular in several fields of statistical science. The dissimilarity between a probability forecast and an outcome is measured by a loss function (scoring rule). Popular example of scoring rule for continuous outcomes is the continuous ranked probability score (CRPS). We consider the case where several competing methods produce online predictions in the form of probability distribution functions. In this paper, the problem of combining probabilistic forecasts is considered in the prediction with expert advice framework. We show that CRPS is a mixable loss function and then the time independent upper bound for the regret of the Vovk's aggregating algorithm using CRPS as a loss function can be obtained. We present the results of numerical experiments illustrating the proposed methods.

arXiv:1902.06838

SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color

We present a novel image editing system that generates images as the user provides free-form mask, sketch and color as an input. Our system consist of a end-to-end trainable convolutional network. Contrary to the existing methods, our system wholly utilizes free-form user input with color and shape. This allows the system to respond to the user's sketch and color input, using it as a guideline to generate an image. In our particular work, we trained network with additional style loss which made it possible to generate realistic results, despite large portions of the image being removed. Our proposed network architecture SC-FEGAN is well suited to generate high quality synthetic image using intuitive user inputs.

arXiv:1902.04260공식 코드 · Papers with Code

Table2answer: Read the database and answer without SQL

Semantic parsing is the task of mapping natural language to logic form. In question answering, semantic parsing can be used to map the question to logic form and execute the logic form to get the answer. One key problem for semantic parsing is the hard label work. We study this problem in another way: we do not use the logic form any more. Instead we only use the schema and answer info. We think that the logic form step can be injected into the deep model. The reason why we think removing the logic form step is possible is that human can do the task without explicit logic form. We use BERT-based model and do the experiment in the WikiSQL dataset, which is a large natural language to SQL dataset. Our experimental evaluations that show that our model can achieves the baseline results in WikiSQL dataset.

arXiv:1902.02162

Adaptive Artificial Intelligent Q&A Platform

The paper presents an approach to build a question and answer system that is capable of processing the information in a large dataset and allows the user to gain knowledge from this dataset by asking questions in natural language form. Key content of this research covers four dimensions which are; Corpus Preprocessing, Question Preprocessing, Deep Neural Network for Answer Extraction and Answer Generation. The system is capable of understanding the question, responds to the user's query in natural language form as well. The goal is to make the user feel as if they were interacting with a person than a machine.

arXiv:1901.06221

Computing Optimal Coarse Correlated Equilibria in Sequential Games

We investigate the computation of equilibria in extensive-form games where ex ante correlation is possible, focusing on correlated equilibria requiring the least amount of communication between the players and the mediator. Motivated by the hardness results on the computation of normal-form correlated equilibria, we introduce the notion of normal-form coarse correlated equilibrium, extending the definition of coarse correlated equilibrium to sequential games. We show that, in two-player games without chance moves, an optimal (e.g., social welfare maximizing) normal-form coarse correlated equilibrium can be computed in polynomial time, and that in general multi-player games (including two-player games with Chance), the problem is NP-hard. For the former case, we provide a polynomial-time algorithm based on the ellipsoid method and also propose a more practical one, which can be efficiently applied to problems of considerable size. Then, we discuss how our algorithm can be extended to games with Chance and games with more than two players.

arXiv:1901.06201공식 코드 · Papers with Code

Optimized Realization of Bayesian Networks in Reduced Normal Form using Latent Variable Model

Bayesian networks in their Factor Graph Reduced Normal Form (FGrn) are a powerful paradigm for implementing inference graphs. Unfortunately, the computational and memory costs of these networks may be considerable, even for relatively small networks, and this is one of the main reasons why these structures have often been underused in practice. In this work, through a detailed algorithmic and structural analysis, various solutions for cost reduction are proposed. An online version of the classic batch learning algorithm is also analyzed, showing very similar results (in an unsupervised context); which is essential even if multilevel structures are to be built. The solutions proposed, together with the possible online learning algorithm, are included in a C++ library that is quite efficient, especially if compared to the direct use of the well-known sum-product and Maximum Likelihood (ML) algorithms. The results are discussed with particular reference to a Latent Variable Model (LVM) structure.

arXiv:1901.04405공식 코드 · Papers with Code

Quadratization in discrete optimization and quantum mechanics

A book about turning high-degree optimization problems into quadratic optimization problems that maintain the same global minimum (ground state). This book explores quadratizations for pseudo-Boolean optimization, perturbative gadgets used in QMA completeness theorems, and also non-perturbative k-local to 2-local transformations used for quantum mechanics, quantum annealing and universal adiabatic quantum computing. The book contains ~70 different Hamiltonian transformations, each of them on a separate page, where the cost (in number of auxiliary binary variables or auxiliary qubits, or number of sub-modular terms, or in graph connectivity, etc.), pros, cons, examples, and references are given. One can therefore look up a quadratization appropriate for the specific term(s) that need to be quadratized, much like using an integral table to look up the integral that needs to be done. This book is therefore useful for writing compilers to transform general optimization problems, into a form that quantum annealing or universal adiabatic quantum computing hardware requires; or for transforming quantum chemistry problems written in the Jordan-Wigner or Bravyi-Kitaev form, into a form where all multi-qubit interactions become 2-qubit pairwise interactions, without changing the desired ground state. Applications cited include computer vision problems (e.g. image de-noising, un-blurring, etc.), number theory (e.g. integer factoring), graph theory (e.g. Ramsey number determination), and quantum chemistry. The book is open source, and anyone can make modifications here: https://github.com/HPQC-LABS/Book_About_Quadratization.

arXiv:1901.03732

The statistical Minkowski distances: Closed-form formula for Gaussian Mixture Models

The traditional Minkowski distances are induced by the corresponding Minkowski norms in real-valued vector spaces. In this work, we propose novel statistical symmetric distances based on the Minkowski's inequality for probability densities belonging to Lebesgue spaces. These statistical Minkowski distances admit closed-form formula for Gaussian mixture models when parameterized by integer exponents. This result extends to arbitrary mixtures of exponential families with natural parameter spaces being cones: This includes the binomial, the multinomial, the zero-centered Laplacian, the Gaussian and the Wishart mixtures, among others. We also derive a Minkowski's diversity index of a normalized weighted set of probability distributions from Minkowski's inequality.

arXiv:1901.03227

Closed-form Expressions for Maximum Mean Discrepancy with Applications to Wasserstein Auto-Encoders

The Maximum Mean Discrepancy (MMD) has found numerous applications in statistics and machine learning, most recently as a penalty in the Wasserstein Auto-Encoder (WAE). In this paper we compute closed-form expressions for estimating the Gaussian kernel based MMD between a given distribution and the standard multivariate normal distribution. This formula reveals a connection to the Baringhaus-Henze-Epps-Pulley (BHEP) statistic of the Henze-Zirkler test and provides further insights about the MMD. We introduce the standardized version of MMD as a penalty for the WAE training objective, allowing for a better interpretability of MMD values and more compatibility across different hyperparameter settings. Next, we propose using a version of batch normalization at the code layer; this has the benefits of making the kernel width selection easier, reducing the training effort, and preventing outliers in the aggregate code distribution. Our experiments on synthetic and real data show that the analytic formulation improves over the commonly used stochastic approximation of the MMD, and demonstrate that code normalization provides significant benefits when training WAEs.

arXiv:1901.02998

Sentence Rewriting for Semantic Parsing

A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology. In this paper, we propose a sentence rewriting based semantic parsing method, which can effectively resolve the mismatch problem by rewriting a sentence into a new form which has the same structure with its target logical form. Specifically, we propose two sentence-rewriting methods for two common types of mismatch: a dictionary-based method for 1-N mismatch and a template-based method for N-1 mismatch. We evaluate our entence rewriting based semantic parser on the benchmark semantic parsing dataset -- WEBQUESTIONS. Experimental results show that our system outperforms the base system with a 3.4% gain in F1, and generates logical forms more accurately and parses sentences more robustly.

arXiv:1901.00612공식 코드 · Papers with Code

Adversarial Learning of a Sampler Based on an Unnormalized Distribution

We investigate adversarial learning in the case when only an unnormalized form of the density can be accessed, rather than samples. With insights so garnered, adversarial learning is extended to the case for which one has access to an unnormalized form u(x) of the target density function, but no samples. Further, new concepts in GAN regularization are developed, based on learning from samples or from u(x). The proposed method is compared to alternative approaches, with encouraging results demonstrated across a range of applications, including deep soft Q-learning.

arXiv:1812.03632공식 코드 · Papers with Code

Statement networks: a power structure narrative as depicted by newspapers

We report a data mining pipeline and subsequent analysis to understand the core periphery power structure created in three national newspapers in Bangladesh, as depicted by statements made by people appearing in news. Statements made by one actor about another actor can be considered a form of public conversation. Named entity recognition techniques can be used to create a temporal actor network from such conversations, which shows some unique structure, and reveals much room for improvement in news reporting and also the top actors' conversation preferences. Our results indicate there is a presence of cliquishness between powerful political leaders when it comes to their appearance in news. We also show how these cohesive cores form through the news articles, and how, over a decade, news cycles change the actors belonging in these groups.

arXiv:1812.03580

Closed-form Inference and Prediction in Gaussian Process State-Space Models

We examine an analytic variational inference scheme for the Gaussian Process State Space Model (GPSSM) - a probabilistic model for system identification and time-series modelling. Our approach performs variational inference over both the system states and the transition function. We exploit Markov structure in the true posterior, as well as an inducing point approximation to achieve linear time complexity in the length of the time series. Contrary to previous approaches, no Monte Carlo sampling is required: inference is cast as a deterministic optimisation problem. In a number of experiments, we demonstrate the ability to model non-linear dynamics in the presence of both process and observation noise as well as to impute missing information (e.g. velocities from raw positions through time), to de-noise, and to estimate the underlying dimensionality of the system. Finally, we also introduce a closed-form method for multi-step prediction, and a novel criterion for assessing the quality of our approximate posterior.

arXiv:1811.08465

Fading of collective attention shapes the evolution of linguistic variants

Language change involves the competition between alternative linguistic forms (1). The spontaneous evolution of these forms typically results in monotonic growths or decays (2, 3) like in winner-take-all attractor behaviors. In the case of the Spanish past subjunctive, the spontaneous evolution of its two competing forms (ended in -ra and -se) was perturbed by the appearance of the Royal Spanish Academy in 1713, which enforced the spelling of both forms as perfectly interchangeable variants (4), at a moment in which the -ra form was dominant (5). Time series extracted from a massive corpus of books (6) reveal that this regulation in fact produced a transient renewed interest for the old form -se which, once faded, left the -ra again as the dominant form up to the present day. We show that time series are successfully explained by a two-dimensional linear model that integrates an imitative and a novelty component. The model reveals that the temporal scale over which collective attention fades is in inverse proportion to the verb frequency. The integration of the two basic mechanisms of imitation and attention to novelty allows to understand diverse competing objects, with lifetimes that range from hours for memes and news (7, 8) to decades for verbs, suggesting the existence of a general mechanism underlying cultural evolution.