PyTorchKR Papers

최신 논문

총 605편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2109.08215공식 코드 · Papers with Code

Pre-trained Gaussian Processes for Bayesian Optimization

Bayesian optimization (BO) has become a popular strategy for global optimization of expensive real-world functions. Contrary to a common expectation that BO is suited to optimizing black-box functions, it actually requires domain knowledge about those functions to deploy BO successfully. Such domain knowledge often manifests in Gaussian process (GP) priors that specify initial beliefs on functions. However, even with expert knowledge, it is non-trivial to quantitatively define a prior. This is especially true for hyperparameter tuning problems on complex machine learning models, where landscapes of tuning objectives are often difficult to comprehend. We seek an alternative practice for setting these functional priors. In particular, we consider the scenario where we have data from similar functions that allow us to pre-train a tighter distribution a priori. We detail what pre-training entails for GPs using a KL divergence based loss function, and propose a new pre-training based BO framework named HyperBO. Theoretically, we show bounded posterior predictions and near-zero regrets for HyperBO without assuming the "ground truth" GP prior is known. To verify our approach in realistic setups, we collect a large multi-task hyperparameter tuning dataset by training tens of thousands of configurations of near-state-of-the-art deep learning models on popular image and text datasets, as well as a protein sequence dataset. Our results show that on average, HyperBO is able to locate good hyperparameters at least 3 times more efficiently than the best competing methods on both our new tuning dataset and existing multi-task BO benchmarks.

arXiv:2109.03349공식 코드 · Papers with Code

Certifiably Optimal Outlier-Robust Geometric Perception: Semidefinite Relaxations and Scalable Global Optimization

We propose the first general and scalable framework to design certifiable algorithms for robust geometric perception in the presence of outliers. Our first contribution is to show that estimation using common robust costs, such as truncated least squares (TLS), maximum consensus, Geman-McClure, Tukey's biweight, among others, can be reformulated as polynomial optimization problems (POPs). By focusing on the TLS cost, our second contribution is to exploit sparsity in the POP and propose a sparse semidefinite programming (SDP) relaxation that is much smaller than the standard Lasserre's hierarchy while preserving empirical exactness, i.e., the SDP recovers the optimizer of the nonconvex POP with an optimality certificate. Our third contribution is to solve the SDP relaxations at an unprecedented scale and accuracy by presenting STRIDE, a solver that blends global descent on the convex SDP with fast local search on the nonconvex POP. Our fourth contribution is an evaluation of the proposed framework on six geometric perception problems including single and multiple rotation averaging, point cloud and mesh registration, absolute pose estimation, and category-level object pose and shape estimation. Our experiments demonstrate that (i) our sparse SDP relaxation is empirically exact with up to 60%-90% outliers across applications; (ii) while still being far from real-time, STRIDE is up to 100 times faster than existing SDP solvers on medium-scale problems, and is the only solver that can solve large-scale SDPs with hundreds of thousands of constraints to high accuracy; (iii) STRIDE safeguards existing fast heuristics for robust estimation (e.g., RANSAC or Graduated Non-Convexity), i.e., it certifies global optimality if the heuristic estimates are optimal, or detects and allows escaping local optima when the heuristic estimates are suboptimal.

arXiv:2108.10859

Cumulative Regret Analysis of the Piyavskii--Shubert Algorithm and Its Variants for Global Optimization

We study the problem of global optimization, where we analyze the performance of the Piyavskii--Shubert algorithm and its variants. For any given time duration $T$, instead of the extensively studied simple regret (which is the difference of the losses between the best estimate up to $T$ and the global minimum), we study the cumulative regret up to time $T$. For $L$-Lipschitz continuous functions, we show that the cumulative regret is $O(L\log T)$. For $H$-Lipschitz smooth functions, we show that the cumulative regret is $O(H)$. We analytically extend our results for functions with Holder continuous derivatives, which cover both the Lipschitz continuous and the Lipschitz smooth functions, individually. We further show that a simpler variant of the Piyavskii-Shubert algorithm performs just as well as the traditional variants for the Lipschitz continuous or the Lipschitz smooth functions. We further extend our results to broader classes of functions, and show that, our algorithm efficiently determines its queries; and achieves nearly minimax optimal (up to log factors) cumulative regret, for general convex or even concave regularity conditions on the extrema of the objective (which encompasses many preceding regularities). We consider further extensions by investigating the performance of the Piyavskii-Shubert variants in the scenarios with unknown regularity, noisy evaluation and multivariate domain.

arXiv:2108.05756

COVINS: Visual-Inertial SLAM for Centralized Collaboration

Collaborative SLAM enables a group of agents to simultaneously co-localize and jointly map an environment, thus paving the way to wide-ranging applications of multi-robot perception and multi-user AR experiences by eliminating the need for external infrastructure or pre-built maps. This article presents COVINS, a novel collaborative SLAM system, that enables multi-agent, scalable SLAM in large environments and for large teams of more than 10 agents. The paradigm here is that each agent runs visual-inertial odomety independently onboard in order to ensure its autonomy, while sharing map information with the COVINS server back-end running on a powerful local PC or a remote cloud server. The server back-end establishes an accurate collaborative global estimate from the contributed data, refining the joint estimate by means of place recognition, global optimization and removal of redundant data, in order to ensure an accurate, but also efficient SLAM process. A thorough evaluation of COVINS reveals increased accuracy of the collaborative SLAM estimates, as well as efficiency in both removing redundant information and reducing the coordination overhead, and demonstrates successful operation in a large-scale mission with 12 agents jointly performing SLAM.

arXiv:2108.02959공식 코드 · Papers with Code

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database. In this way, when updating the deployed model, we can bypass the inflexible and time-consuming feature re-extraction process. However, the old feature space that needs to be compatible is not ideal and faces the distribution discrepancy problem with the new space caused by different supervision losses. In this work, we propose a global optimization Dual-Tuning method to obtain feature compatibility against different networks and losses. A feature-level prototype loss is proposed to explicitly align two types of embedding features, by transferring global prototype information. Furthermore, we design a component-level mutual structural regularization to implicitly optimize the feature intrinsic structure. Experimental results on million-scale datasets demonstrate that our Dual-Tuning is able to obtain feature compatibility without sacrificing performance. (Our code will be avaliable at https://github.com/yanbai1993/Dual-Tuning)

arXiv:2108.02289

High dimensional Bayesian Optimization Algorithm for Complex System in Time Series

At present, high-dimensional global optimization problems with time-series models have received much attention from engineering fields. Since it was proposed, Bayesian optimization has quickly become a popular and promising approach for solving global optimization problems. However, the standard Bayesian optimization algorithm is insufficient to solving the global optimal solution when the model is high-dimensional. Hence, this paper presents a novel high dimensional Bayesian optimization algorithm by considering dimension reduction and different dimension fill-in strategies. Most existing literature about Bayesian optimization algorithms did not discuss the sampling strategies to optimize the acquisition function. This study proposed a new sampling method based on both the multi-armed bandit and random search methods while optimizing the acquisition function. Besides, based on the time-dependent or dimension-dependent characteristics of the model, the proposed algorithm can reduce the dimension evenly. Then, five different dimension fill-in strategies were discussed and compared in this study. Finally, to increase the final accuracy of the optimal solution, the proposed algorithm adds a local search based on a series of Adam-based steps at the final stage. Our computational experiments demonstrated that the proposed Bayesian optimization algorithm could achieve reasonable solutions with excellent performances for high dimensional global optimization problems with a time-series optimal control model.

arXiv:2108.00568

FLASH: Fast Neural Architecture Search with Hardware Optimization

Neural architecture search (NAS) is a promising technique to design efficient and high-performance deep neural networks (DNNs). As the performance requirements of ML applications grow continuously, the hardware accelerators start playing a central role in DNN design. This trend makes NAS even more complicated and time-consuming for most real applications. This paper proposes FLASH, a very fast NAS methodology that co-optimizes the DNN accuracy and performance on a real hardware platform. As the main theoretical contribution, we first propose the NN-Degree, an analytical metric to quantify the topological characteristics of DNNs with skip connections (e.g., DenseNets, ResNets, Wide-ResNets, and MobileNets). The newly proposed NN-Degree allows us to do training-free NAS within one second and build an accuracy predictor by training as few as 25 samples out of a vast search space with more than 63 billion configurations. Second, by performing inference on the target hardware, we fine-tune and validate our analytical models to estimate the latency, area, and energy consumption of various DNN architectures while executing standard ML datasets. Third, we construct a hierarchical algorithm based on simplicial homology global optimization (SHGO) to optimize the model-architecture co-design process, while considering the area, latency, and energy consumption of the target hardware. We demonstrate that, compared to the state-of-the-art NAS approaches, our proposed hierarchical SHGO-based algorithm enables more than four orders of magnitude speedup (specifically, the execution time of the proposed algorithm is about 0.1 seconds). Finally, our experimental evaluations show that FLASH is easily transferable to different hardware architectures, thus enabling us to do NAS on a Raspberry Pi-3B processor in less than 3 seconds.

arXiv:2107.14370

Otimizacao de pesos e funcoes de ativacao de redes neurais aplicadas na previsao de series temporais

Neural Networks have been applied for time series prediction with good experimental results that indicate the high capacity to approximate functions with good precision. Most neural models used in these applications use activation functions with fixed parameters. However, it is known that the choice of activation function strongly influences the complexity and performance of the neural network and that a limited number of activation functions have been used. In this work, we propose the use of a family of free parameter asymmetric activation functions for neural networks and show that this family of defined activation functions satisfies the requirements of the universal approximation theorem. A methodology for the global optimization of this family of activation functions with free parameter and the weights of the connections between the processing units of the neural network is used. The central idea of the proposed methodology is to simultaneously optimize the weights and the activation function used in a multilayer perceptron network (MLP), through an approach that combines the advantages of simulated annealing, tabu search and a local learning algorithm, with the purpose of improving performance in the adjustment and forecasting of time series. We chose two learning algorithms: backpropagation with the term momentum (BPM) and LevenbergMarquardt (LM).

arXiv:2107.13864공식 코드 · Papers with Code

Continuation Newton methods with deflation techniques for global optimization problems

The global minimum point of an optimization problem is of interest in engineering fields and it is difficult to be found, especially for a nonconvex large-scale optimization problem. In this article, we consider a new memetic algorithm for this problem. That is to say, we use the continuation Newton method with the deflation technique to find multiple stationary points of the objective function and use those found stationary points as the initial seeds of the evolutionary algorithm, other than the random initial seeds of the known evolutionary algorithms. Meanwhile, in order to retain the usability of the derivative-free method and the fast convergence of the gradient-based method, we use the automatic differentiation technique to compute the gradient and replace the Hessian matrix with its finite difference approximation. According to our numerical experiments, this new algorithm works well for unconstrained optimization problems and finds their global minima efficiently, in comparison to the other representative global optimization methods such as the multi-start methods (the built-in subroutine GlobalSearch.m of MATLAB R2021b, GLODS and VRBBO), the branch-and-bound method (Couenne, a state-of-the-art open-source solver for mixed integer nonlinear programming problems), and the derivative-free algorithms (CMA-ES and MCS).

arXiv:2107.09521

On the Design of Complex EM Devices and Systems through the System-by-Design Paradigm -- A Framework for Dealing with the Computational Complexity

The System-by-Design (SbD) is an emerging engineering framework for the optimization-driven design of complex electromagnetic (EM) devices and systems. More specifically, the computational complexity of the design problem at hand is addressed by means of a suitable selection and integration of functional blocks comprising problem-dependent and computationally-efficient modeling and analysis tools as well as reliable prediction and optimization strategies. Thanks to the suitable re-formulation of the problem at hand as an optimization one, the profitable minimum-size coding of the degrees-of-freedom (DoFs), the "smart" replacement of expensive full-wave (FW) simulators with proper surrogate models (SMs), which yield fast yet accurate predictions starting from minimum size/reduced CPU-costs training sets, a favorable "environment" for an optimal exploitation of the features of global optimization tools in sampling wide/complex/nonlinear solution spaces is built. This research summary is then aimed at (i) providing a comprehensive description of the SbD framework and of its pillar concepts and strategies, (ii) giving useful guidelines for its successful customization and application to different EM design problems characterized by different levels of computational complexity, (iii) envisaging future trends and advances in this fascinating and high-interest (because of its relevant and topical industrial and commercial implications) topic. Representative benchmarks concerned with the synthesis of complex EM systems are presented to highlight advantages and potentialities as well as current limitations of the SbD paradigm.

arXiv:2107.08467공식 코드 · Papers with Code

GoTube: Scalable Stochastic Verification of Continuous-Depth Models

We introduce a new stochastic verification algorithm that formally quantifies the behavioral robustness of any time-continuous process formulated as a continuous-depth model. Our algorithm solves a set of global optimization (Go) problems over a given time horizon to construct a tight enclosure (Tube) of the set of all process executions starting from a ball of initial states. We call our algorithm GoTube. Through its construction, GoTube ensures that the bounding tube is conservative up to a desired probability and up to a desired tightness. GoTube is implemented in JAX and optimized to scale to complex continuous-depth neural network models. Compared to advanced reachability analysis tools for time-continuous neural networks, GoTube does not accumulate overapproximation errors between time steps and avoids the infamous wrapping effect inherent in symbolic techniques. We show that GoTube substantially outperforms state-of-the-art verification tools in terms of the size of the initial ball, speed, time-horizon, task completion, and scalability on a large set of experiments. GoTube is stable and sets the state-of-the-art in terms of its ability to scale to time horizons well beyond what has been previously possible.

arXiv:2107.08035

Testing Surrogate-Based Optimization with the Fortified Branin-Hoo Extended to Four Dimensions

Some popular functions used to test global optimization algorithms have multiple local optima, all with the same value, making them all global optima. It is easy to make them more challenging by fortifying them via adding a localized bump at the location of one of the optima. In previous work the authors illustrated this for the Branin-Hoo function and the popular differential evolution algorithm, showing that the fortified Branin-Hoo required an order of magnitude more function evaluations. This paper examines the effect of fortifying the Branin-Hoo function on surrogate-based optimization, which usually proceeds by adaptive sampling. Two algorithms are considered. The EGO algorithm, which is based on a Gaussian process (GP) and an algorithm based on radial basis functions (RBF). EGO is found to be more frugal in terms of the number of required function evaluations required to identify the correct basin, but it is expensive to run on a desktop, limiting the number of times the runs could be repeated to establish sound statistics on the number of required function evaluations. The RBF algorithm was cheaper to run, providing more sound statistics on performance. A four-dimensional version of the Branin-Hoo function was introduced in order to assess the effect of dimensionality. It was found that the difference between the ordinary function and the fortified one was much more pronounced for the four-dimensional function compared to the two dimensional one.

arXiv:2107.06581

A Granular Sieving Algorithm for Deterministic Global Optimization

A gradient-free deterministic method is developed to solve global optimization problems for Lipschitz continuous functions defined in arbitrary path-wise connected compact sets in Euclidean spaces. The method can be regarded as granular sieving with synchronous analysis in both the domain and range of the objective function. With straightforward mathematical formulation applicable to both univariate and multivariate objective functions, the global minimum value and all the global minimizers are located through two decreasing sequences of compact sets in, respectively, the domain and range spaces. The algorithm is easy to implement with moderate computational cost. The method is tested against extensive benchmark functions in the literature. The experimental results show remarkable effectiveness and applicability of the algorithm.

arXiv:2107.02080

Uso de GSO cooperativos com decaimentos de pesos para otimizacao de redes neurais

Training of Artificial Neural Networks is a complex task of great importance in supervised learning problems. Evolutionary Algorithms are widely used as global optimization techniques and these approaches have been used for Artificial Neural Networks to perform various tasks. An optimization algorithm, called Group Search Optimizer (GSO), was proposed and inspired by the search behaviour of animals. In this article we present two new hybrid approaches: CGSO-Hk-WD and CGSO-Sk-WD. Cooperative GSOs are based on the divide-and-conquer paradigm, employing cooperative behaviour between GSO groups to improve the performance of the standard GSO. We also apply the weight decay strategy (WD, acronym for Weight Decay) to increase the generalizability of the networks. The results show that cooperative GSOs are able to achieve better performance than traditional GSO for classification problems in benchmark datasets such as Cancer, Diabetes, Ecoli and Glass datasets.

arXiv:2107.00332

Learned Global Optimization for Inverse Scattering Problems -- Matching Global Search with Computational Efficiency

The computationally-efficient solution of fully non-linear microwave inverse scattering problems (ISPs) is addressed. An innovative System-by-Design (SbD) based method is proposed to enable, for the first time to the best of the authors knowledge, an effective, robust, and time-efficient exploitation of an evolutionary algorithm (EA) to perform the global minimization of the data-mismatch cost function. According to the SbD paradigm as suitably applied to ISPs, the proposed approach founds on (i) a smart re-formulation of the ISP based on the definition of a minimum-dimensionality and representative set of degrees-of-freedom (DoFs) and on (ii) the artificial-intelligence (AI)-driven integration of a customized global search technique with a digital twin (DT) predictor based on the Gaussian Process (GP) theory. Representative numerical and experimental results are provided to assess the effectiveness and the efficiency of the proposed approach also in comparison with competitive state-of-the-art inversion techniques.

arXiv:2106.15216

A Non-parametric View of FedAvg and FedProx: Beyond Stationary Points

Federated Learning (FL) is a promising decentralized learning framework and has great potentials in privacy preservation and in lowering the computation load at the cloud. Recent work showed that FedAvg and FedProx - the two widely-adopted FL algorithms - fail to reach the stationary points of the global optimization objective even for homogeneous linear regression problems. Further, it is concerned that the common model learned might not generalize well locally at all in the presence of heterogeneity. In this paper, we analyze the convergence and statistical efficiency of FedAvg and FedProx, addressing the above two concerns. Our analysis is based on the standard non-parametric regression in a reproducing kernel Hilbert space (RKHS), and allows for heterogeneous local data distributions and unbalanced local datasets. We prove that the estimation errors, measured in either the empirical norm or the RKHS norm, decay with a rate of 1/t in general and exponentially for finite-rank kernels. In certain heterogeneous settings, these upper bounds also imply that both FedAvg and FedProx achieve the optimal error rate. To further analytically quantify the impact of the heterogeneity at each client, we propose and characterize a novel notion-federation gain, defined as the reduction of the estimation error for a client to join the FL. We discover that when the data heterogeneity is moderate, a client with limited local data can benefit from a common model with a large federation gain. Numerical experiments further corroborate our theoretical findings.

arXiv:2106.06304공식 코드 · Papers with Code

Automated Configuration of Genetic Algorithms by Tuning for Anytime Performance

Finding the best configuration of algorithms' hyperparameters for a given optimization problem is an important task in evolutionary computation. We compare in this work the results of four different hyperparameter tuning approaches for a family of genetic algorithms on 25 diverse pseudo-Boolean optimization problems. More precisely, we compare previously obtained results from a grid search with those obtained from three automated configuration techniques: iterated racing, mixed-integer parallel efficient global optimization, and mixed-integer evolutionary strategies. Using two different cost metrics, expected running time and the area under the empirical cumulative distribution function curve, we find that in several cases the best configurations with respect to expected running time are obtained when using the area under the empirical cumulative distribution function curve as the cost metric during the configuration process. Our results suggest that even when interested in expected running time performance, it might be preferable to use anytime performance measures for the configuration task. We also observe that tuning for expected running time is much more sensitive with respect to the budget that is allocated to the target algorithms.

arXiv:2106.01779

Preparation of Many-body Ground States by Time Evolution with Variational Microscopic Magnetic Fields and Incomplete Interactions

State preparation is of fundamental importance in quantum physics, which can be realized by constructing the quantum circuit as a unitary that transforms the initial state to the target, or implementing a quantum control protocol to evolve to the target state with a designed Hamiltonian. In this work, we study the latter on quantum many-body systems by the time evolution with fixed couplings and variational magnetic fields. In specific, we consider to prepare the ground states of the Hamiltonians containing certain interactions that are missing in the Hamiltonians for the time evolution. An optimization method is proposed to optimize the magnetic fields by "fine-graining" the discretization of time, in order to gain high precision and stability. The back propagation technique is utilized to obtain the gradients of the fields against the logarithmic fidelity. Our method is tested on preparing the ground state of Heisenberg chain with the time evolution by the XY and Ising interactions, and its performance surpasses two baseline methods that use local and global optimization strategies, respectively. Our work can be applied and generalized to other quantum models such as those defined on higher dimensional lattices. It enlightens to reduce the complexity of the required interactions for implementing quantum control or other tasks in quantum information and computation by means of optimizing the magnetic fields.

arXiv:2105.11796

Automatic Dynamic Parallelotope Bundles for Reachability Analysis of Nonlinear Systems

Reachable set computation is an important technique for the verification of safety properties of dynamical systems. In this paper, we investigate reachable set computation for discrete nonlinear systems based on parallelotope bundles. The algorithm relies on computing an upper bound on the supremum of a nonlinear function over a rectangular domain, which has been traditionally done using Bernstein polynomials. We strive to remove the manual step of parallelotope template selection to make the method fully automatic. Furthermore, we show that changing templates dynamically during computations cans improve accuracy. To this end, we investigate two techniques for generating the template directions. The first technique approximates the dynamics as a linear transformation and generates templates using this linear transformation. The second technique uses Principal Component Analysis (PCA) of sample trajectories for generating templates. We have implemented our approach in a Python-based tool called Kaa and improve its performance by two main enhancements. The tool is modular and use two types of global optimization solvers, the first using Bernstein polynomials and the second using NASA's Kodiak nonlinear optimization library. Second, we leverage the natural parallelism of the reachability algorithm and parallelize the Kaa implementation. We demonstrate the improved accuracy of our approach on several standard nonlinear benchmark systems.

논문 ID: publication/4323133

Localization in Wireless Sensor Networks using Particle Swarm Optimization

This paper proposes a novel and computationally efficient global optimization method based on swarm intelligence for locating nodes in a WSN environment. The mean squared range errors of all neighbouring anchor nodes is taken as the objective function for this non linear optimization problem. The Particle Swarm Optimization (PSO) is a high performance stochastic global optimization tool that ensures the minimization of the objective function, without being trapped into local optima. The easy implementation and low memory requirement features of PSO make it suitable for highly resource constrained WSN environments. Computational experiments on data drawn from simulated WSNs show better convergence characteristics than the existing Simulated Annealing based WSN localization.