PyTorchKR Papers

최신 논문

총 605편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1907.10383

Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties

Learning robot controllers by minimizing a black-box objective cost using Bayesian optimization (BO) can be time-consuming and challenging. It is very often the case that some roll-outs result in failure behaviors, causing premature experiment detention. In such cases, the designer is forced to decide on heuristic cost penalties because the acquired data is often scarce, or not comparable with that of the stable policies. To overcome this, we propose a Bayesian model that captures exactly what we know about the cost of unstable controllers prior to data collection: Nothing, except that it should be a somewhat large number. The resulting Bayesian model, approximated with a Gaussian process, predicts high cost values in regions where failures are likely to occur. In this way, the model guides the BO exploration toward regions of stability. We demonstrate the benefits of the proposed model in several illustrative and statistical synthetic benchmarks, and also in experiments on a real robotic platform. In addition, we propose and experimentally validate a new BO method to account for unknown constraints. Such method is an extension of Max-Value Entropy Search, a recent information-theoretic method, to solve unconstrained global optimization problems.

arXiv:1907.10300공식 코드 · Papers with Code

Sparse Optimization on Measures with Over-parameterized Gradient Descent

Minimizing a convex function of a measure with a sparsity-inducing penalty is a typical problem arising, e.g., in sparse spikes deconvolution or two-layer neural networks training. We show that this problem can be solved by discretizing the measure and running non-convex gradient descent on the positions and weights of the particles. For measures on a $d$-dimensional manifold and under some non-degeneracy assumptions, this leads to a global optimization algorithm with a complexity scaling as $\log(1/\epsilon)$ in the desired accuracy $\epsilon$, instead of $\epsilon^{-d}$ for convex methods. The key theoretical tools are a local convergence analysis in Wasserstein space and an analysis of a perturbed mirror descent in the space of measures. Our bounds involve quantities that are exponential in $d$ which is unavoidable under our assumptions.

arXiv:1907.05346공식 코드 · Papers with Code

A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts

End-to-end Task-oriented Dialogue Systems (TDSs) have attracted a lot of attention for their superiority (e.g., in terms of global optimization) over pipeline modularized TDSs. Previous studies on end-to-end TDSs use a single-module model to generate responses for complex dialogue contexts. However, no model consistently outperforms the others in all cases. We propose a neural Modular Task-oriented Dialogue System(MTDS) framework, in which a few expert bots are combined to generate the response for a given dialogue context. MTDS consists of a chair bot and several expert bots. Each expert bot is specialized for a particular situation, e.g., one domain, one type of action of a system, etc. The chair bot coordinates multiple expert bots and adaptively selects an expert bot to generate the appropriate response. We further propose a Token-level Mixture-of-Expert (TokenMoE) model to implement MTDS, where the expert bots predict multiple tokens at each timestamp and the chair bot determines the final generated token by fully taking into consideration the outputs of all expert bots. Both the chair bot and the expert bots are jointly trained in an end-to-end fashion. To verify the effectiveness of TokenMoE, we carry out extensive experiments on a benchmark dataset. Compared with the baseline using a single-module model, our TokenMoE improves the performance by 8.1% of inform rate and 0.8% of success rate.

arXiv:1906.09524

Fractional-order Backpropagation Neural Networks: Modified Fractional-order Steepest Descent Method for Family of Backpropagation Neural Networks

This paper offers a novel mathematical approach, the modified Fractional-order Steepest Descent Method (FSDM) for training BackPropagation Neural Networks (BPNNs); this differs from the majority of the previous approaches and as such. A promising mathematical method, fractional calculus, has the potential to assume a prominent role in the applications of neural networks and cybernetics because of its inherent strengths such as long-term memory, nonlocality, and weak singularity. Therefore, to improve the optimization performance of classic first-order BPNNs, in this paper we study whether it could be possible to modified FSDM and generalize classic first-order BPNNs to modified FSDM based Fractional-order Backpropagation Neural Networks (FBPNNs). Motivated by this inspiration, this paper proposes a state-of-the-art application of fractional calculus to implement a modified FSDM based FBPNN whose reverse incremental search is in the negative directions of the approximate fractional-order partial derivatives of the square error. At first, the theoretical concept of a modified FSDM based FBPNN is described mathematically. Then, the mathematical proof of the fractional-order global optimal convergence, an assumption of the structure, and the fractional-order multi-scale global optimization of a modified FSDM based FBPNN are analysed in detail. Finally, we perform comparative experiments and compare a modified FSDM based FBPNN with a classic first-order BPNN, i.e., an example function approximation, fractional-order multi-scale global optimization, and two comparative performances with real data. The more efficient optimal searching capability of the fractional-order multi-scale global optimization of a modified FSDM based FBPNN to determine the global optimal solution is the major advantage being superior to a classic first-order BPNN.

arXiv:1906.08851

A Seft-adaptive Multicellular GEP Algorithm Based On Fuzzy Control For Function Optimization

To improve the global optimization ability of traditional GEP algorithm, a Multicellular gene expression programming algorithm based on fuzzy control (Multicellular GEP Algorithm Based On Fuzzy Control, MGEP-FC) is proposed. The MGEP-FC algorithm describes the size of cross rate, mutation rate and real number mutation rate by constructing fuzzy membership function. According to the concentration and dispersion of individual fitness values in population, the crossover rate, mutation rate and real number set mutation rate of genetic operation are dynamically adjusted. In order to make the diversity of the population continue in the iterative process, a new genetic operation scheme is designed, which combines the new individuals with the parent population to build a temporary population, and the diversity of the temporary and subpopulation are optimized. The results of 12 Benchmark optimization experiments show that the MGEP-FC algorithm has been greatly improved in stability, global convergence and optimization speed.

arXiv:1906.07848공식 코드 · Papers with Code

Symbolic regression by uniform random global search

Symbolic regression (SR) is a data analysis problem where we search for the mathematical expression that best fits a numerical dataset. It is a global optimization problem. The most popular approach to SR is by genetic programming (SRGP). It is a common paradigm to compare an algorithm's performance to that of random search, but the data comparing SRGP to random search is lacking. We describe a novel algorithm for SR, namely SR by uniform random global search (SRURGS), also known as pure random search. We conduct experiments comparing SRURGS with SRGP using 100 randomly generated equations. Our results suggest that a SRGP is faster than SRURGS in producing equations with good R^2 for simple problems. However, our experiments suggest that SRURGS is more robust than SRGP, able to produce good output in more challenging problems. As SRURGS is arguably the simplest global search algorithm, we believe it should serve as a control algorithm against which other symbolic regression algorithms are compared. SRURGS has only one tuning parameter, and is conceptually very simple, making it a useful tool in solving SR problems. The method produces random equations, which is useful for the generation of symbolic regression benchmark problems. We have released well documented and open-source python code, currently under formal peer-review, so that interested researchers can deploy the tool in practice.

arXiv:1906.07843

Simulator-based training of generative models for the inverse design of metasurfaces

Metasurfaces are subwavelength-structured artificial media that can shape and localize electromagnetic waves in unique ways. The inverse design of these devices is a non-convex optimization problem in a high dimensional space, making global optimization a major challenge. We present a new type of population-based global optimization algorithm for metasurfaces that is enabled by the training of a generative neural network. The loss function used for backpropagation depends on the generated pattern layouts, their efficiencies, and efficiency gradients, which are calculated by the adjoint variables method using forward and adjoint electromagnetic simulations. We observe that the distribution of devices generated by the network continuously shifts towards high performance design space regions over the course of optimization. Upon training completion, the best generated devices have efficiencies comparable to or exceeding the best devices designed using standard topology optimization. Our proposed global optimization algorithm can generally apply to other gradient-based optimization problems in optics, mechanics and electronics.

arXiv:1906.06498

Global optimization via inverse distance weighting and radial basis functions

Global optimization problems whose objective function is expensive to evaluate can be solved effectively by recursively fitting a surrogate function to function samples and minimizing an acquisition function to generate new samples. The acquisition step trades off between seeking for a new optimization vector where the surrogate is minimum (exploitation of the surrogate) and looking for regions of the feasible space that have not yet been visited and that may potentially contain better values of the objective function (exploration of the feasible space). This paper proposes a new global optimization algorithm that uses a combination of inverse distance weighting (IDW) and radial basis functions (RBF) to construct the acquisition function. Rather arbitrary constraints that are simple to evaluate can be easily taken into account. Compared to Bayesian optimization, the proposed algorithm, that we call GLIS (GLobal minimum using Inverse distance weighting and Surrogate radial basis functions), is competitive and computationally lighter, as we show in a set of benchmark global optimization and hyperparameter tuning problems. MATLAB and Python implementations of GLIS are available at \url{http://cse.lab.imtlucca.it/~bemporad/glis}.

arXiv:1906.04680

Efficient Kernel-based Subsequence Search for User Identification from Walking Activity

This paper presents an efficient approach for subsequence search in data streams. The problem consists in identifying coherent repetitions of a given reference time-series, eventually multi-variate, within a longer data stream. Dynamic Time Warping (DTW) is the metric most widely used to implement pattern query, but its computational complexity is a well-known issue. In this paper we present an approach aimed at learning a kernel able to approximate DTW to be used for efficiently analyse streaming data collected from wearable sensors, reducing the burden of computation. Contrary to kernel, DTW allows for comparing time series with different length. Thus, to use a kernel, a feature embedding is used to represent a time-series as a fixed length vector. Each vector component is the DTW between the given time-series and a set of 'basis' series, usually randomly chosen. The vector size is the number of basis series used for the feature embedding. Searching for the portion of the data stream minimizing the DTW with the reference subsequence leads to a global optimization problem. The proposed approach has been validated on a benchmark dataset related to the identification of users depending on their walking activity. A comparison with a traditional DTW implementation is also provided.

arXiv:1906.04157

Global optimization of dielectric metasurfaces using a physics-driven neural network

We present a global optimizer, based on a conditional generative neural network, which can output ensembles of highly efficient topology-optimized metasurfaces operating across a range of parameters. A key feature of the network is that it initially generates a distribution of devices that broadly samples the design space, and then shifts and refines this distribution towards favorable design space regions over the course of optimization. Training is performed by calculating the forward and adjoint electromagnetic simulations of outputted devices and using the subsequent efficiency gradients for backpropagation. With metagratings operating across a range of wavelengths and angles as a model system, we show that devices produced from the trained generative network have efficiencies comparable to or better than the best devices produced by adjoint-based topology optimization, while requiring less computational cost. Our reframing of adjoint-based optimization to the training of a generative neural network applies generally to physical systems that can utilize gradients to improve performance.

arXiv:1906.00101

Testing that a Local Optimum of the Likelihood is Globally Optimum using Reparameterized Embeddings

Many mathematical imaging problems are posed as non-convex optimization problems. When numerically tractable global optimization procedures are not available, one is often interested in testing ex post facto whether or not a locally convergent algorithm has found the globally optimal solution. When the problem is formulated in terms of maximizing the likelihood function under a statistical model for the measurements, one can construct a statistical test that a local maximum is in fact the global maximum. A one-sided test is proposed for the case that the statistical model is a member of the generalized location family of probability distributions, a condition often satisfied in imaging and other inverse problems. We propose a general method for improving the accuracy of the test by reparameterizing the likelihood function to embed its domain into a higher dimensional parameter space. We show that the proposed global maximum testing method results in improved accuracy and reduced computation for a physically-motivated joint-inverse problem arising in camera-blur estimation.

arXiv:1905.07458

Neural Metric Learning for Fast End-to-End Relation Extraction

Relation extraction (RE) is an indispensable information extraction task in several disciplines. RE models typically assume that named entity recognition (NER) is already performed in a previous step by another independent model. Several recent efforts, under the theme of end-to-end RE, seek to exploit inter-task correlations by modeling both NER and RE tasks jointly. Earlier work in this area commonly reduces the task to a table-filling problem wherein an additional expensive decoding step involving beam search is applied to obtain globally consistent cell labels. In efforts that do not employ table-filling, global optimization in the form of CRFs with Viterbi decoding for the NER component is still necessary for competitive performance. We introduce a novel neural architecture utilizing the table structure, based on repeated applications of 2D convolutions for pooling local dependency and metric-based features, that improves on the state-of-the-art without the need for global optimization. We validate our model on the ADE and CoNLL04 datasets for end-to-end RE and demonstrate $\approx 1\%$ gain (in F-score) over prior best results with training and testing times that are seven to ten times faster --- the latter highly advantageous for time-sensitive end user applications.

arXiv:1905.07288

Approximation of the objective insensitivity regions using Hierarchic Memetic Strategy coupled with Covariance Matrix Adaptation Evolutionary Strategy

One of the most challenging types of ill-posedness in global optimization is the presence of insensitivity regions in design parameter space, so the identification of their shape will be crucial, if ill-posedness is irrecoverable. Such problems may be solved using global stochastic search followed by post-processing of a local sample and a local objective approximation. We propose a new approach of this type composed of Hierarchic Memetic Strategy (HMS) powered by the Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) well-known as an effective, self-adaptable stochastic optimization algorithm and we leverage the distribution density knowledge it accumulates to better identify and separate insensitivity regions. The results of benchmarks prove that the improved HMS-CMA-ES strategy is effective in both the total computational cost and the accuracy of insensitivity region approximation. The reference data for the tests was obtained by means of a well-known effective strategy of multimodal stochastic optimization called the Niching Evolutionary Algorithm 2 (NEA2), that also uses CMA-ES as a component.

arXiv:1812.03457

Minima distribution for global optimization

This paper establishes a strict mathematical relationship between an arbitrary continuous function on a compact set and its global minima, like the well-known first order optimality condition for convex and differentiable functions. By introducing a class of nascent minima distribution functions that is only related to the target function and the given compact set, we construct a sequence that monotonically converges to the global minima on that given compact set. Then, we further consider some various sequences of sets where each sequence monotonically shrinks from the original compact set to the set of all global minimizers, and the shrink rate can be determined for continuously differentiable functions. Finally, we provide a different way of constructing the nascent minima distribution functions.

arXiv:1905.03350

Bayesian Optimization using Deep Gaussian Processes

Bayesian Optimization using Gaussian Processes is a popular approach to deal with the optimization of expensive black-box functions. However, because of the a priori on the stationarity of the covariance matrix of classic Gaussian Processes, this method may not be adapted for non-stationary functions involved in the optimization problem. To overcome this issue, a new Bayesian Optimization approach is proposed. It is based on Deep Gaussian Processes as surrogate models instead of classic Gaussian Processes. This modeling technique increases the power of representation to capture the non-stationarity by simply considering a functional composition of stationary Gaussian Processes, providing a multiple layer structure. This paper proposes a new algorithm for Global Optimization by coupling Deep Gaussian Processes and Bayesian Optimization. The specificities of this optimization method are discussed and highlighted with academic test cases. The performance of the proposed algorithm is assessed on analytical test cases and an aerospace design optimization problem and compared to the state-of-the-art stationary and non-stationary Bayesian Optimization approaches.

arXiv:1904.13241

Fourier Transform Approach to Machine Learning II: Fourier Clustering

We propose a Fourier-based approach for optimization of several clustering algorithms. Mathematically, clusters data can be described by a density function represented by the Dirac mixture distribution. The density function can be smoothed by applying the Fourier transform and a Gaussian filter. The determination of the optimal standard deviation of the Gaussian filter will be accomplished by the use of a convergence criterion related to the correlation between the smoothed and the original density functions. In principle, the optimal smoothed density function exhibits local maxima, which correspond to the cluster centroids. Thus, the complex task of finding the centroids of the clusters is simplified by the detection of the peaks of the smoothed density function. A multiple sliding windows procedure is used to detect the peaks. The remarkable accuracy of the proposed algorithm demonstrates its capability as a reliable general method for enhancement of the clustering performance, its global optimization and also removing the initialization problem in many clustering methods.

arXiv:1904.12672

Efficient Computation of Expected Hypervolume Improvement Using Box Decomposition Algorithms

In the field of multi-objective optimization algorithms, multi-objective Bayesian Global Optimization (MOBGO) is an important branch, in addition to evolutionary multi-objective optimization algorithms (EMOAs). MOBGO utilizes Gaussian Process models learned from previous objective function evaluations to decide the next evaluation site by maximizing or minimizing an infill criterion. A common criterion in MOBGO is the Expected Hypervolume Improvement (EHVI), which shows a good performance on a wide range of problems, with respect to exploration and exploitation. However, so far it has been a challenge to calculate exact EHVI values efficiently. In this paper, an efficient algorithm for the computation of the exact EHVI for a generic case is proposed. This efficient algorithm is based on partitioning the integration volume into a set of axis-parallel slices. Theoretically, the upper bound time complexities are improved from previously $O (n^2)$ and $O(n^3)$, for two- and three-objective problems respectively, to $\Theta(n\log n)$, which is asymptotically optimal. This article generalizes the scheme in higher dimensional case by utilizing a new hyperbox decomposition technique, which was proposed by D{\"a}chert et al, EJOR, 2017. It also utilizes a generalization of the multilayered integration scheme that scales linearly in the number of hyperboxes of the decomposition. The speed comparison shows that the proposed algorithm in this paper significantly reduces computation time. Finally, this decomposition technique is applied in the calculation of the Probability of Improvement (PoI).

arXiv:1904.12535

Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction

In this paper, we consider the problem of open information extraction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain. We focus on four types of valuable intermediate structures (Relation, Attribute, Description, and Concept), and propose a unified knowledge expression form, SAOKE, to express them. We publicly release a data set which contains more than forty thousand sentences and the corresponding facts in the SAOKE format labeled by crowd-sourcing. To our knowledge, this is the largest publicly available human labeled data set for open information extraction tasks. Using this labeled SAOKE data set, we train an end-to-end neural model using the sequenceto-sequence paradigm, called Logician, to transform sentences into facts. For each sentence, different to existing algorithms which generally focus on extracting each single fact without concerning other possible facts, Logician performs a global optimization over all possible involved facts, in which facts not only compete with each other to attract the attention of words, but also cooperate to share words. An experimental study on various types of open domain relation extraction tasks reveals the consistent superiority of Logician to other states-of-the-art algorithms. The experiments verify the reasonableness of SAOKE format, the valuableness of SAOKE data set, the effectiveness of the proposed Logician model, and the feasibility of the methodology to apply end-to-end learning paradigm on supervised data sets for the challenging tasks of open information extraction.

arXiv:1904.10523

A neural network-based framework for financial model calibration

A data-driven approach called CaNN (Calibration Neural Network) is proposed to calibrate financial asset price models using an Artificial Neural Network (ANN). Determining optimal values of the model parameters is formulated as training hidden neurons within a machine learning framework, based on available financial option prices. The framework consists of two parts: a forward pass in which we train the weights of the ANN off-line, valuing options under many different asset model parameter settings; and a backward pass, in which we evaluate the trained ANN-solver on-line, aiming to find the weights of the neurons in the input layer. The rapid on-line learning of implied volatility by ANNs, in combination with the use of an adapted parallel global optimization method, tackles the computation bottleneck and provides a fast and reliable technique for calibrating model parameters while avoiding, as much as possible, getting stuck in local minima. Numerical experiments confirm that this machine-learning framework can be employed to calibrate parameters of high-dimensional stochastic volatility models efficiently and accurately.

arXiv:1904.09368

Derivative-Free Global Optimization Algorithms: Population based Methods and Random Search Approaches

In this paper, we will provide an introduction to the derivative-free optimization algorithms which can be potentially applied to train deep learning models. Existing deep learning model training is mostly based on the back propagation algorithm, which updates the model variables layers by layers with the gradient descent algorithm or its variants. However, the objective functions of deep learning models to be optimized are usually non-convex and the gradient descent algorithms based on the first-order derivative can get stuck into the local optima very easily. To resolve such a problem, various local or global optimization algorithms have been proposed, which can help improve the training of deep learning models greatly. The representative examples include the Bayesian methods, Shubert-Piyavskii algorithm, Direct, LIPO, MCS, GA, SCE, DE, PSO, ES, CMA-ES, hill climbing and simulated annealing, etc. This is a follow-up paper of [18], and we will introduce the population based optimization algorithms, e.g., GA, SCE, DE, PSO, ES and CMA-ES, and random search algorithms, e.g., hill climbing and simulated annealing, in this paper. For the introduction to the other derivative-free optimization algorithms, please refer to [18] for more information.