PyTorchKR Papers

최신 논문

총 605편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2012.08863

On The Verification of Neural ODEs with Stochastic Guarantees

We show that Neural ODEs, an emerging class of time-continuous neural networks, can be verified by solving a set of global-optimization problems. For this purpose, we introduce Stochastic Lagrangian Reachability (SLR), an abstraction-based technique for constructing a tight Reachtube (an over-approximation of the set of reachable states over a given time-horizon), and provide stochastic guarantees in the form of confidence intervals for the Reachtube bounds. SLR inherently avoids the infamous wrapping effect (accumulation of over-approximation errors) by performing local optimization steps to expand safe regions instead of repeatedly forward-propagating them as is done by deterministic reachability methods. To enable fast local optimizations, we introduce a novel forward-mode adjoint sensitivity method to compute gradients without the need for backpropagation. Finally, we establish asymptotic and non-asymptotic convergence rates for SLR.

arXiv:2012.05613

From particle swarm optimization to consensus based optimization: stochastic modeling and mean-field limit

In this paper we consider a continuous description based on stochastic differential equations of the popular particle swarm optimization (PSO) process for solving global optimization problems and derive in the large particle limit the corresponding mean-field approximation based on Vlasov-Fokker-Planck-type equations. The disadvantage of memory effects induced by the need to store the local best position is overcome by the introduction of an additional differential equation describing the evolution of the local best. A regularization process for the global best permits to formally derive the respective mean-field description. Subsequently, in the small inertia limit, we compute the related macroscopic hydrodynamic equations that clarify the link with the recently introduced consensus based optimization (CBO) methods. Several numerical examples illustrate the mean field process, the small inertia limit and the potential of this general class of global optimization methods.

arXiv:2012.04951

Conjugate Mixture Models for Clustering Multimodal Data

The problem of multimodal clustering arises whenever the data are gathered with several physically different sensors. Observations from different modalities are not necessarily aligned in the sense there there is no obvious way to associate or to compare them in some common space. A solution may consist in considering multiple clustering tasks independently for each modality. The main difficulty with such an approach is to guarantee that the unimodal clusterings are mutually consistent. In this paper we show that multimodal clustering can be addressed within a novel framework, namely conjugate mixture models. These models exploit the explicit transformations that are often available between an unobserved parameter space (objects) and each one of the observation spaces (sensors). We formulate the problem as a likelihood maximization task and we derive the associated conjugate expectation-maximization algorithm. The convergence properties of the proposed algorithm are thoroughly investigated. Several local/global optimization techniques are proposed in order to increase its convergence speed. Two initialization strategies are proposed and compared. A consistent model-selection criterion is proposed. The algorithm and its variants are tested and evaluated within the task of 3D localization of several speakers using both auditory and visual data.

arXiv:2012.04350공식 코드 · Papers with Code

MANGO: A Mask Attention Guided One-Stage Scene Text Spotter

Recently end-to-end scene text spotting has become a popular research topic due to its advantages of global optimization and high maintainability in real applications. Most methods attempt to develop various region of interest (RoI) operations to concatenate the detection part and the sequence recognition part into a two-stage text spotting framework. However, in such framework, the recognition part is highly sensitive to the detected results (e.g.), the compactness of text contours). To address this problem, in this paper, we propose a novel Mask AttentioN Guided One-stage text spotting framework named MANGO, in which character sequences can be directly recognized without RoI operation. Concretely, a position-aware mask attention module is developed to generate attention weights on each text instance and its characters. It allows different text instances in an image to be allocated on different feature map channels which are further grouped as a batch of instance features. Finally, a lightweight sequence decoder is applied to generate the character sequences. It is worth noting that MANGO inherently adapts to arbitrary-shaped text spotting and can be trained end-to-end with only coarse position information (e.g.), rectangular bounding box) and text annotations. Experimental results show that the proposed method achieves competitive and even new state-of-the-art performance on both regular and irregular text spotting benchmarks, i.e., ICDAR 2013, ICDAR 2015, Total-Text, and SCUT-CTW1500.

arXiv:2012.03618

Global Riemannian Acceleration in Hyperbolic and Spherical Spaces

We further research on the accelerated optimization phenomenon on Riemannian manifolds by introducing accelerated global first-order methods for the optimization of $L$-smooth and geodesically convex (g-convex) or $\mu$-strongly g-convex functions defined on the hyperbolic space or a subset of the sphere. For a manifold other than the Euclidean space, these are the first methods to \emph{globally} achieve the same rates as accelerated gradient descent in the Euclidean space with respect to $L$ and $\epsilon$ (and $\mu$ if it applies), up to log factors. Due to the geometric deformations, our rates have an extra factor, depending on the initial distance $R$ to a minimizer and the curvature $K$, with respect to Euclidean accelerated algorithms As a proxy for our solution, we solve a constrained non-convex Euclidean problem, under a condition between convexity and \emph{quasar-convexity}, of independent interest. Additionally, for any Riemannian manifold of bounded sectional curvature, we provide reductions from optimization methods for smooth and g-convex functions to methods for smooth and strongly g-convex functions and vice versa. We also reduce global optimization to optimization over bounded balls where the effect of the curvature is reduced.

arXiv:2009.06123

Phase-Only Beam Broadening of Contiguous Uniform Subarrayed Arrays Utilizing Three Metaheuristic Global Optimization Techniques

Radar beam broadening provides continuous coverage of a wider angular extent. While many methods have been published that address beam broadening of traditional (nonsubarrayed) arrays, there is a knowledge gap in the published literature with respect to efficient and effective beam broadening of contiguous uniform subarrayed arrays. This paper presents efficient and effective methods for beam broadening of contiguous uniform subarrayed arrays where elements of the array are grouped together to have the same element excitations. Particularly, this paper focuses on phase-only optimization to preserve maximum power output. The high dimensionality of the solution space of possible phase settings causes brute force techniques to be infeasible for exhaustively evaluating the entire space. This paper presents three metaheuristic global optimization techniques that efficiently and effectively search for optimal phase values in this large solution space that satisfy the desired broadened pattern. The techniques presented in this paper are simulated annealing, genetic algorithm with elitism, and particle swarm optimization. These techniques are evaluated on idealized 40x40 and 80x80 element rectangular arrays with 5x5 element subarrays. The results of this study show that as configured in this paper the simulated annealing and particle swarm techniques outshine the genetic algorithm technique for 40x40 and 80x80 rectangular arrays grouped into contiguous uniform 5x5 element subarrays.

arXiv:2002.09183

Analysis of performance criteria for optimization based bearing only target tracking algorithms

Target tracking problem has many practical applications in real life. In submarines, target tracking is done using, preferably, passive sensors. These sensors measure only the bearing angles between the observed target and the ownship. Therefore, this problem is generally referred as bearing only target tracking or target motion analysis. The classical approach is to use a state observer based filter, i.e. Extended Kalman Filter, to estimate the range, course and speed of the target, using only the bearings. In recent studies, the problem is solved as a global optimization problem by utilizing evolutionary algorithms with respect to some objective functions. In this study, we investigate the effect of the commonly used cost functions on the performance of the TMA algorithms. Particularly, we investigate the cost functions based on bearing differences and equidistant line segments. The simulation results show that the latter gives a sub-optimal solution to the target motion analysis problem, compared to the former.

arXiv:1906.00920

Optimising portfolio diversification and dimensionality

A new framework for portfolio diversification is introduced which goes beyond the classical mean-variance approach and portfolio allocation strategies such as risk parity. It is based on a novel concept called portfolio dimensionality that connects diversification to the non-Gaussianity of portfolio returns and can typically be defined in terms of the ratio of risk measures which are homogenous functions of equal degree. The latter arises naturally due to our requirement that diversification measures should be leverage invariant. We introduce this new framework and argue the benefits relative to existing measures of diversification in the literature, before addressing the question of optimizing diversification or, equivalently, dimensionality. Maximising portfolio dimensionality leads to highly non-trivial optimization problems with objective functions which are typically non-convex and potentially have multiple local optima. Two complementary global optimization algorithms are thus presented. For problems of moderate size and more akin to asset allocation problems, a deterministic Branch and Bound algorithm is developed, whereas for problems of larger size a stochastic global optimization algorithm based on Gradient Langevin Dynamics is given. We demonstrate analytically and through numerical experiments that the framework reflects the desired properties often discussed in the literature.

arXiv:1809.08321

A Step-by-Step Guide to Using BioNetFit

BioNetFit is a software tool designed for solving parameter identification problems that arise in the development of rule-based models. It solves these problems through curve fitting (i.e., nonlinear regression). BioNetFit is compatible with deterministic and stochastic simulators that accept BioNetGen language (BNGL)-formatted files as inputs, such those available within the BioNetGen framework. BioNetFit can be used on a laptop or standalone multicore workstation as well as on many Linux clusters, such as those that use the Slurm Workload Manager to schedule jobs. BioNetFit implements a metaheuristic population-based global optimization procedure, an evolutionary algorithm (EA), to minimize a user-defined objective function, such as a residual sum of squares (RSS) function. BioNetFit also implements a bootstrapping procedure for determining confidence intervals for parameter estimates. Here, we provide step-by-step instructions for using BioNetFit to estimate the values of parameters of a BNGL-encoded model and to define bootstrap confidence intervals. The process entails the use of several plain-text files, which are processed by BioNetFit and BioNetGen. In general, these files include 1) one or more EXP files, which each contains (experimental) data to be used in parameter identification/bootstrapping; 2) a BNGL file containing a model section, which defines a (rule-based) model, and an actions section, which defines simulation protocols that generate GDAT and/or SCAN files with model predictions corresponding to the data in the EXP file(s); and 3) a CONF file that configures the fitting/bootstrapping job and that defines algorithmic parameter settings.

arXiv:1809.04632

Efficient Global Optimization using Deep Gaussian Processes

Efficient Global Optimization (EGO) is widely used for the optimization of computationally expensive black-box functions. It uses a surrogate modeling technique based on Gaussian Processes (Kriging). However, due to the use of a stationary covariance, Kriging is not well suited for approximating non stationary functions. This paper explores the integration of Deep Gaussian processes (DGP) in EGO framework to deal with the non-stationary issues and investigates the induced challenges and opportunities. Numerical experimentations are performed on analytical problems to highlight the different aspects of DGP and EGO.

arXiv:1807.10180

Global optimization using Gaussian Processes to estimate biological parameters from image data

Parameter estimation is a major challenge in computational modeling of biological processes. This is especially the case in image-based modeling where the inherently quantitative output of the model is measured against image data, which is typically noisy and non-quantitative. In addition, these models can have a high computational cost, limiting the number of feasible simulations, and therefore rendering most traditional parameter estimation methods unsuitable. In this paper, we present a pipeline that uses Gaussian process learning to estimate biological parameters from noisy, non-quantitative image data when the model has a high computational cost. This approach is first successfully tested on a parametric function with the goal of retrieving the original parameters. We then apply it to estimating parameters in a biological setting by fitting artificial in-situ hybridization (ISH) data of the developing murine limb bud. We expect that this method will be of use in a variety of modeling scenarios where quantitative data is missing and the use of standard parameter estimation approaches in biological modeling is prohibited by the computational cost of the model.

arXiv:1805.08524

Globally Optimized Mutual Influence Aware Ranking in E-Commerce Search

In web search, mutual influences between documents have been studied from the perspective of search result diversification. But the methods in web search is not directly applicable to e-commerce search because of their differences. And little research has been done on the mutual influences between items in e-commerce search. We propose a global optimization framework for mutual influence aware ranking in e-commerce search. Our framework directly optimizes the Gross Merchandise Volume (GMV) for ranking, and decomposes ranking into two tasks. The first task is mutual influence aware purchase probability estimation. We propose a global feature extension method to incorporate mutual influences into the features of an item. We also use Recurrent Neural Network (RNN) to capture influences related to ranking orders in purchase probability estimation. The second task is to find the best ranking order based on the purchase probability estimations. We treat the second task as a sequence generation problem and solved it using the beam search algorithm. We performed online A/B test on a large e-commerce search engine. The results show that our method brings a 5% increase in GMV for the search engine over a strong baseline.

arXiv:1801.05116

Designing Patient-Specific Optimal Neurostimulation Patterns for Seizure Suppression

Neurostimulation is a promising therapy for abating epileptic seizures. However, it is extremely difficult to identify optimal stimulation patterns experimentally. In this study human recordings are used to develop a functional 24 neuron network statistical model of hippocampal connectivity and dynamics. Spontaneous seizure-like activity is induced in-silico in this reconstructed neuronal network. The network is then used as a testbed to design and validate a wide range of neurostimulation patterns. Commonly used periodic trains were not able to permanently abate seizures at any frequency. A simulated annealing global optimization algorithm was then used to identify an optimal stimulation pattern which successfully abated 92% of seizures. Finally, in a fully responsive, or "closed-loop" neurostimulation paradigm, the optimal stimulation successfully prevented the network from entering the seizure state. We propose that the framework presented here for algorithmically identifying patient-specific neurostimulation patterns can greatly increase the efficacy of neurostimulation devices for seizures.

arXiv:1502.02963

An Analysis of the Heston Stochastic Volatility Model: Implementation and Calibration using Matlab

This paper analyses the implementation and calibration of the Heston Stochastic Volatility Model. We first explain how characteristic functions can be used to estimate option prices. Then we consider the implementation of the Heston model, showing that relatively simple solutions can lead to fast and accurate vanilla option prices. We also perform several calibration tests, using both local and global optimization. Our analyses show that straightforward setups deliver good calibration results. All calculations are carried out in Matlab and numerical examples are included in the paper to facilitate the understanding of mathematical concepts.

arXiv:2011.14427

Architectural Adversarial Robustness: The Case for Deep Pursuit

Despite their unmatched performance, deep neural networks remain susceptible to targeted attacks by nearly imperceptible levels of adversarial noise. While the underlying cause of this sensitivity is not well understood, theoretical analyses can be simplified by reframing each layer of a feed-forward network as an approximate solution to a sparse coding problem. Iterative solutions using basis pursuit are theoretically more stable and have improved adversarial robustness. However, cascading layer-wise pursuit implementations suffer from error accumulation in deeper networks. In contrast, our new method of deep pursuit approximates the activations of all layers as a single global optimization problem, allowing us to consider deeper, real-world architectures with skip connections such as residual networks. Experimentally, our approach demonstrates improved robustness to adversarial noise.

arXiv:2011.13094

Combinatorial Bayesian Optimization with Random Mapping Functions to Convex Polytopes

Bayesian optimization is a popular method for solving the problem of global optimization of an expensive-to-evaluate black-box function. It relies on a probabilistic surrogate model of the objective function, upon which an acquisition function is built to determine where next to evaluate the objective function. In general, Bayesian optimization with Gaussian process regression operates on a continuous space. When input variables are categorical or discrete, an extra care is needed. A common approach is to use one-hot encoded or Boolean representation for categorical variables which might yield a combinatorial explosion problem. In this paper we present a method for Bayesian optimization in a combinatorial space, which can operate well in a large combinatorial space. The main idea is to use a random mapping which embeds the combinatorial space into a convex polytope in a continuous space, on which all essential process is performed to determine a solution to the black-box optimization in the combinatorial space. We describe our combinatorial Bayesian optimization algorithm and present its regret analysis. Numerical experiments demonstrate that our method shows satisfactory performance compared to existing methods.

arXiv:2011.11365공식 코드 · Papers with Code

A Learning-based Optimization Algorithm:Image Registration Optimizer Network

Remote sensing image registration is valuable for image-based navigation system despite posing many challenges. As the search space of registration is usually non-convex, the optimization algorithm, which aims to search the best transformation parameters, is a challenging step. Conventional optimization algorithms can hardly reconcile the contradiction of simultaneous rapid convergence and the global optimization. In this paper, a novel learning-based optimization algorithm named Image Registration Optimizer Network (IRON) is proposed, which can predict the global optimum after single iteration. The IRON is trained by a 3D tensor (9x9x9), which consists of similar metric values. The elements of the 3D tensor correspond to the 9x9x9 neighbors of the initial parameters in the search space. Then, the tensor's label is a vector that points to the global optimal parameters from the initial parameters. Because of the special architecture, the IRON could predict the global optimum directly for any initialization. The experimental results demonstrate that the proposed algorithm performs better than other classical optimization algorithms as it has higher accuracy, lower root of mean square error (RMSE), and more efficiency. Our IRON codes are available for further study.https://www.github.com/jaxwangkd04/IRON

arXiv:2011.06780

A differential evolution-based optimization tool for interplanetary transfer trajectory design

The extremely sensitive and highly nonlinear search space of interplanetary transfer trajectory design bring about big challenges on global optimization. As a representative, the current known best solution of the global trajectory optimization problem (GTOP) designed by the European space agency (ESA) is very hard to be found. To deal with this difficulty, a powerful differential evolution-based optimization tool named COoperative Differential Evolution (CODE) is proposed in this paper. CODE employs a two-stage evolutionary process, which concentrates on learning global structure in the earlier process, and tends to self-adaptively learn the structures of different local spaces. Besides, considering the spatial distribution of global optimum on different problems and the gradient information on different variables, a multiple boundary check technique has been employed. Also, Covariance Matrix Adaptation Evolutionary Strategies (CMA-ES) is used as a local optimizer. The previous studies have shown that a specific swarm intelligent optimization algorithm usually can solve only one or two GTOP problems. However, the experimental test results show that CODE can find the current known best solutions of Cassini1 and Sagas directly, and the cooperation with CMA-ES can solve Cassini2, GTOC1, Messenger (reduced) and Rosetta. For the most complicated Messenger (full) problem, even though CODE cannot find the current known best solution, the found best solution with objective function equaling to 3.38 km/s is still a level that other swarm intelligent algorithms cannot easily reach.

arXiv:2011.04026공식 코드 · Papers with Code

Pathwise Conditioning of Gaussian Processes

As Gaussian processes are used to answer increasingly complex questions, analytic solutions become scarcer and scarcer. Monte Carlo methods act as a convenient bridge for connecting intractable mathematical expressions with actionable estimates via sampling. Conventional approaches for simulating Gaussian process posteriors view samples as draws from marginal distributions of process values at finite sets of input locations. This distribution-centric characterization leads to generative strategies that scale cubically in the size of the desired random vector. These methods are prohibitively expensive in cases where we would, ideally, like to draw high-dimensional vectors or even continuous sample paths. In this work, we investigate a different line of reasoning: rather than focusing on distributions, we articulate Gaussian conditionals at the level of random variables. We show how this pathwise interpretation of conditioning gives rise to a general family of approximations that lend themselves to efficiently sampling Gaussian process posteriors. Starting from first principles, we derive these methods and analyze the approximation errors they introduce. We, then, ground these results by exploring the practical implications of pathwise conditioning in various applied settings, such as global optimization and reinforcement learning.

arXiv:2011.01048

Ridge regression with adaptive additive rectangles and other piecewise functional templates

We propose an $L_{2}$-based penalization algorithm for functional linear regression models, where the coefficient function is shrunk towards a data-driven shape template $\gamma$, which is constrained to belong to a class of piecewise functions by restricting its basis expansion. In particular, we focus on the case where $\gamma$ can be expressed as a sum of $q$ rectangles that are adaptively positioned with respect to the regression error. As the problem of finding the optimal knot placement of a piecewise function is nonconvex, the proposed parametrization allows to reduce the number of variables in the global optimization scheme, resulting in a fitting algorithm that alternates between approximating a suitable template and solving a convex ridge-like problem. The predictive power and interpretability of our method is shown on multiple simulations and two real world case studies.