The advancement of artificial intelligence has cast a new light on the development of optimization algorithm. This paper proposes to learn a two-phase (including a minimization phase and an escaping phase) global optimization algorithm for smooth non-convex functions. For the minimization phase, a model-driven deep learning method is developed to learn the update rule of descent direction, which is formalized as a nonlinear combination of historical information, for convex functions. We prove that the resultant algorithm with the proposed adaptive direction guarantees convergence for convex functions. Empirical study shows that the learned algorithm significantly outperforms some well-known classical optimization algorithms, such as gradient descent, conjugate descent and BFGS, and performs well on ill-posed functions. The escaping phase from local optimum is modeled as a Markov decision process with a fixed escaping policy. We further propose to learn an optimal escaping policy by reinforcement learning. The effectiveness of the escaping policies is verified by optimizing synthesized functions and training a deep neural network for CIFAR image classification. The learned two-phase global optimization algorithm demonstrates a promising global search capability on some benchmark functions and machine learning tasks.
Objective: Estimation of the global optima of multiple model parameters is valuable in imaging to form a reliable diagnostic image. Given non convexity of the objective function, it is challenging to avoid from different local minima. Methods: We first formulate the global searching of multiply parameters to be a k-D move in the parametric space, and convert parameters updating to be state-action decision-making problem. We proposed a novel Deep Q-learning of Model Parameters (DQMP) method for global optimization of model parameters by updating the parameter configurations through actions that…
Department of Computer Science and Engineering UC San Diego（计算机科学与工程系 UC San Diego）；Department of Computer Science and Engineering UC Santa Cruz（计算机科学与工程系 UC Santa Cruz）
In this work, we propose a meta algorithm that can solve a multivariate global optimization problem using univariate global optimizers. Although the univariate global optimization does not receive much attention compared to the multivariate case, which is more emphasized in academia and industry; we show that it is still relevant and can be directly used to solve problems of multivariate optimization. We also provide the corresponding regret bounds in terms of the time horizon $T$ and the average regret of the univariate optimizer, when it is robust against nonnegative noises with robust regre…
KU Leuven（鲁汶大学）；Télécom Paris（巴黎电信学院）；Institut Polytechnique de Paris（巴黎理工学院）
This paper introduces a new extragradient-type algorithm for a class of nonconvex-nonconcave minimax problems. It is well-known that finding a local solution for general minimax problems is computationally intractable. This observation has recently motivated the study of structures sufficient for convergence of first order methods in the more general setting of variational inequalities when the so-called weak Minty variational inequality (MVI) holds. This problem class captures non-trivial structures as we demonstrate with examples, for which a large family of existing algorithms provably conv…
Recent advances in GPU accelerated global and detail placement have reduced the time to solution by an order of magnitude. This advancement allows us to leverage data driven optimization (such as Reinforcement Learning) in an effort to improve the final quality of placement results. In this work we augment state-of-the-art, force-based global placement solvers with a reinforcement learning agent trained to improve the final detail placed Half Perimeter Wire Length (HPWL). We propose novel control schemes with either global or localized control of the placement process. We then train reinforcem…
Microsoft Research New England（微软新英格兰研究院）；University of California Irvine（加州大学欧文分校）；University of California Berkeley（加州大学伯克利分校）；Cornell University（康奈尔大学）
We analyze stochastic gradient descent for optimizing non-convex functions. In many cases for non-convex functions the goal is to find a reasonable local minimum, and the main concern is that gradient updates are trapped in saddle points. In this paper we identify strict saddle property for non-convex problem that allows for efficient optimization. Using this property we show that stochastic gradient descent converges to a local minimum in a polynomial number of iterations. To the best of our knowledge this is the first work that gives global convergence guarantees for stochastic gradient desc…
Pohang University of Science and Technology（浦项科技大学）；BARO AI（巴罗人工智能公司）
Bayesian optimization is a sample-efficient method for finding a global optimum of an expensive-to-evaluate black-box function. A global solution is found by accumulating a pair of query point and its function value, repeating these two procedures: (i) modeling a surrogate function; (ii) maximizing an acquisition function to determine where next to query. Convergence guarantees are only valid when the global optimizer of the acquisition function is found at each round and selected as the next query point. In practice, however, local optimizers of an acquisition function are also used, since se…
Dimer-Enhanced Optimization: A First-Order Approach to Escaping Saddle Points in Neural Network Training
School of Bioengineering, Qilu University of Technology (Shandong Academy of Sciences)（青岛科技大学生物工程学院）；Shandong Provincial Key Laboratory of Biophysics, Institute of Biophysics, Dezhou University（山东省生物物理重点实验室，生物物理研究所，德州市大学）；Shandong Provincial Hospital, Shandong First Medical University（山东省人民医院，山东第一医科大学）
University of Jinan（济南大学）；Quan Cheng Laboratory（泉城实验室）；The University of Suwon（水原大学）；Victoria University of Wellington（惠灵顿维多利亚大学）；Cainiao Network（菜鸟网络）
Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. However, the complex real-world problems, especially when the global optimum is desired, could be very far from the a priori assumptions because of their diversities, causing unexpected obstacles. In this study, we propose a generative adversarial net-based broad-spectrum global optimizer (OPT-GAN) which estimates the distribution of optimum gradually,…
The multi-level, multi-disciplinary and multi-fidelity optimization framework developed at Bombardier Aviation has shown great results to explore efficient and competitive aircraft configurations. This optimization framework has been developed within the Isight software, the latter offers a set of ready-to-use optimizers. Unfortunately, the computational effort required by the Isight optimizers can be prohibitive with respect to the requirements of an industrial context. In this paper, a constrained Bayesian optimization optimizer, namely the super efficient global optimization with mixture of…
In this paper, we study the problem of optimizing a two-layer artificial neural network that best fits a training dataset. We look at this problem in the setting where the number of parameters is greater than the number of sampled points. We show that for a wide class of differentiable activation functions (this class involves "almost" all functions which are not piecewise linear), we have that first-order optimal solutions satisfy global optimality provided the hidden layer is non-singular. Our results are easily extended to hidden layers given by a flat matrix from that of a square matrix. R…
Oden Institute（奥登研究所）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Task learning in neural networks typically requires finding a globally optimal minimizer to a loss function objective. Conventional designs of swarm based optimization methods apply a fixed update rule, with possibly an adaptive step-size for gradient descent based optimization. While these methods gain huge success in solving different optimization problems, there are some cases where these schemes are either inefficient or suffering from local-minimum. We present a new particle-swarm-based framework utilizing Gaussian Process Regression to learn the underlying dynamical process of descent. T…
Second-order optimizers hold intriguing potential for deep learning, but suffer from increased cost and sensitivity to the non-convexity of the loss surface as compared to gradient-based approaches. We introduce a coordinate descent method to train deep neural networks for classification tasks that exploits global convexity of the cross-entropy loss in the weights of the linear layer. Our hybrid Newton/Gradient Descent (NGD) method is consistent with the interpretation of hidden layers as providing an adaptive basis and the linear layer as providing an optimal fit of the basis to data. By alte…
Non-convex optimization is ubiquitous in modern machine learning. Researchers devise non-convex objective functions and optimize them using off-the-shelf optimizers such as stochastic gradient descent and its variants, which leverage the local geometry and update iteratively. Even though solving non-convex functions is NP-hard in the worst case, the optimization quality in practice is often not an issue -- optimizers are largely believed to find approximate global minima. Researchers hypothesize a unified explanation for this intriguing phenomenon: most of the local minima of the practically-u…
Learning to optimize has emerged as a powerful framework for various optimization and machine learning tasks. Current such "meta-optimizers" often learn in the space of continuous optimization algorithms that are point-based and uncertainty-unaware. To overcome the limitations, we propose a meta-optimizer that learns in the algorithmic space of both point-based and population-based optimization algorithms. The meta-optimizer targets at a meta-loss function consisting of both cumulative regret and entropy. Specifically, we learn and interpret the update formula through a population of LSTMs emb…
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gaussian process bandits, simple control objectives, global optimization benchmarks and hyper-parameter tuning tasks. Up to the training horizon, the learned optimizers learn to trade-off exploration and exploitation, and compare favourably with heavily engineered Bayesian optimization packages for hyper…
Local Entropy Search over Descent Sequences for Bayesian Optimization
Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Germany（机械工程数据科学研究所，亚琛工业大学，德国）；Learning Systems and Robotics Lab, Technical University of Munich, Germany（学习系统与机器人实验室，慕尼黑技术大学，德国）
Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Center for Nonlinear Studies（非线性研究中心）
Barren plateau landscapes correspond to gradients that vanish exponentially in the number of qubits. Such landscapes have been demonstrated for variational quantum algorithms and quantum neural networks with either deep circuits or global cost functions. For obvious reasons, it is expected that gradient-based optimizers will be significantly affected by barren plateaus. However, whether or not gradient-free optimizers are impacted is a topic of debate, with some arguing that gradient-free approaches are unaffected by barren plateaus. Here we show that, indeed, gradient-free optimizers do not s…
University of Tabriz（大不里士大学）；Shahed University（沙希德大学）；Virginia Commonwealth University（弗吉尼亚联邦大学）；Australian Catholic University（澳大利亚天主教大学）
This paper proposes a novel nature-inspired meta-heuristic algorithm called the Golden Tortoise Beetle Optimizer (GTBO) to solve optimization problems. It mimics golden tortoise beetle's behavior of changing colors to attract opposite sex for mating and its protective strategy that uses a kind of anal fork to deter predators. The algorithm is modeled based on the beetle's dual attractiveness and survival strategy to generate new solutions for optimization problems. To measure its performance, the proposed GTBO is compared with five other nature-inspired evolutionary algorithms on 24 well-known…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Beckman Institute（贝克曼研究所）
In this paper, we develop a convolutional neural network model to predict the mechanical properties of a two-dimensional checkerboard composite quantitatively. The checkerboard composite possesses two phases, one phase is soft and ductile while the other is stiff and brittle. The ground-truth data used in the training process are obtained from finite element analyses under the assumption of plane stress. Monte Carlo simulations and central limit theorem are used to find the size of the dataset needed. Once the training process is completed, the developed model is validated using data unseen du…
Easy-to-use programming interfaces paired with cloud-scale processing engines have enabled big data system users to author arbitrarily complex analytical jobs over massive volumes of data. However, as the complexity and scale of analytical jobs increase, they encounter a number of unforeseen problems, hotspots with large intermediate data on temporary storage, longer job recovery time after failures, and worse query optimizer estimates being examples of issues that we are facing at Microsoft. To address these issues, we propose Phoebe, an efficient learning-based checkpoint optimizer. Given a …
High-Dimensional and Incomplete matrices, which usually contain a large amount of valuable latent information, can be well represented by a Latent Factor Analysis model. The performance of an LFA model heavily rely on its optimization process. Thereby, some prior studies employ the Particle Swarm Optimization to enhance an LFA model's optimization process. However, the particles within the swarm follow the static evolution paths and only share the global best information, which limits the particles' searching area to cause sub-optimum issue. To address this issue, this paper proposes a Dynamic…
University of South Florida（南佛罗里达大学）；Mississippi State University（密西西比州立大学）
Federated Learning (FL) is a promising framework for performing privacy-preserving, distributed learning with a set of clients. However, the data distribution among clients often exhibits non-IID, i.e., distribution shift, which makes efficient optimization difficult. To tackle this problem, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by increasing the performance of the global model. However, almost all algorithms leverage Empirical Risk Minimization (ERM) to be the local optimizer, which is easy to make the global model fall into a sharp valley and…
Taming the Instability: A Robust Second-Order Optimizer for Federated Learning over Non-IID Data
Key Laboratory of Collaborative Intelligence Systems of Ministry of Education, Xidian University（西安电子科技大学教育部协同智能系统重点实验室）；Centre for Frontier AI Research, Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所前沿人工智能研究中心）；State Key Laboratory of ISN, School of Cyber Engineering, Xidian University（西安电子科技大学网络与信息安全学院综合业务网理论及关键技术国家重点实验室）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Department of Computing Technologies, Swinburne University of Technology（斯威本科技大学计算技术系）
The Coronavirus, known as COVID-19, which appeared in 2019 in China, has significantly affected global health and become a huge burden on health institutions all over the world. These effects are continuing today. One strategy for limiting the virus's transmission is to have an early diagnosis of suspected cases and take appropriate measures before the disease spreads further. This work aims to diagnose and show the probability of getting infected by the disease according to textual clinical data. In this work, we used five machine learning techniques (GWO_MLP, GWO_CMLP, MGWO_MLP, FDO_MLP, FDO…
