检索结果-内蒙古大学图书馆

Learning Constrained Parametric differentiable Predictive Control Policies With Guarantees

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2024年第6期54卷 3596-3607页

作者： Drgona, Jan Tuor, Aaron Vrabie, Draguna Pacific Northwest Natl Lab Phys & Computat Sci Div Richland WA 99352 USA

We present differentiable predictive control (DPC), a method for offline learning of constrained neural control policies for nonlinear dynamical systems with performance guarantees. We show that the sensitivities of the parametric optimal control problem can be used to obtain direct policy gradients. Specifically, we employ automatic differentiation (AD) to efficiently compute the sensitivities of the model predictive control (MPC) objective function and constraints penalties. To guarantee safety upon deployment, we derive probabilistic guarantees on closed-loop stability and constraint satisfaction based on indicator functions and Hoeffding's inequality. We empirically demonstrate that the proposed method can learn neural control policies for various parametric optimal control tasks. In particular, we show that the proposed DPC method can stabilize systems with unstable dynamics, track time-varying references, and satisfy nonlinear state and input constraints. Our DPC method has practical time savings compared to alternative approaches for fast and memory-efficient controller design. Specifically, DPC does not depend on a supervisory controller as opposed to approximate MPC based on imitation learning. We demonstrate that, without losing performance, DPC is scalable with greatly reduced demands on memory and computation compared to implicit and explicit MPC while being more sample efficient than model-free reinforcement learning (RL) algorithms.

关键词： Predictive control Optimization Computational modeling programming Sensitivity Optimal control Closed loop systems differentiable programming learning for control parametric optimal control policy optimization (PO)

来源：评论

学校读者我要写书评

暂无评论

Learning to optimize:A tutorial for continuous and mixed-integer optimization

引用

Science China Mathematics 2024年第6期67卷 1191-1262页

作者： Xiaohan Chen Jialin Liu Wotao Yin Decision Intelligence Lab Alibaba DAMO AcademyBellevueWA98004USA

Learning to optimize(L2O)stands at the intersection of traditional optimization and machine learning,utilizing the capabilities of machine learning to enhance conventional optimization *** real-world optimization problems frequently share common structures,L2O provides a tool to exploit these structures for better or faster *** tutorial dives deep into L2O techniques,introducing how to accelerate optimization algorithms,promptly estimate the solutions,or even reshape the optimization problem itself,making it more adaptive to real-world *** considering the prerequisites for successful applications of L2O and the structure of the optimization problems at hand,this tutorial provides a comprehensive guide for practitioners and researchers alike.

关键词： AI for mathematics(AI4Math) learning to optimize algorithm unrolling plug-and-play methods differentiable programming machine learning for combinatorial optimization(ML4CO)

来源：评论

学校读者我要写书评

暂无评论

Optimization of Distribution Feeder Topology: a Differential programming Learning Approach

Optimization of Distribution Feeder Topology: a Differential...

引用

IEEE-Power-and-Energy-Society General Meeting (PESGM)

作者： Sigler, Devon Biagioni, David Emami, Patrick Zamzam, Ahmed Knueven, Bernard Natl Renewable Energy Lab Golden CO 80401 USA Maplewell Energy Broomfield CO USA

ISBN: (纸本)9781665464413

This paper presents a gradient based method for optimizing distribution feeder network topology under load uncertainty. We recast the optimal network reconfiguration problem as a learning problem where edge weights of a graph are learned to produce an optimized spanning tree for a distribution network. Using recent methods published on differentiable programming, we provide a data driven method for learning these weights. We test our method on 100 variations of an IEEE 15 -bus test system. Our results show that our method outperforms more traditional mathematical programming -based approaches.

关键词： Optimal Network Reconfiguration Stochastic programming differentiable programming

来源：评论

学校读者我要写书评

暂无评论

Distributions for Compositionally Differentiating Parametric Discontinuities

引用

PROCEEDINGS OF THE ACM ON programming LANGUAGES-PACMPL 2024年第OOPSLA期8卷 893-922页

作者： Michel, Jesse Mu, Kevin Yang, Xuanda Bangaru, Sai Praveen Collins, Elias Rojas Bernstein, Gilbert Ragan-Kelley, Jonathan Carbin, Michael Li, Tzu-Mao MIT Cambridge MA 02139 USA Univ Washington Seattle WA USA Univ Calif San Diego San Diego CA USA Univ Washington Cambridge MA USA

Computations in physical simulation, computer graphics, and probabilistic inference often require the differentiation of discontinuous processes due to contact, occlusion, and changes at a point in time. Popular differentiable programming languages, such as PyTorch and JAX, ignore discontinuities during differentiation. This is incorrect for parametric discontinuities-conditionals containing at least one real-valued parameter and at least one variable of integration. We introduce Potto, the first differentiable first-order programming language to soundly differentiate parametric discontinuities. We present a denotational semantics for programs and program derivatives and show the two accord. We describe the implementation of Potto, which enables separate compilation of programs. Our prototype implementation overcomes previous compile-time bottlenecks achieving an 88.1x and 441.2x speed up in compile time and a 2.5x and 7.9x speed up in runtime, respectively, on two increasingly large image stylization benchmarks. We showcase Potto by implementing a prototype differentiable renderer with separately compiled shaders.

关键词： differentiable programming Denotational Semantics differentiable Rendering Distribution Theory Probabilistic programming

来源：评论

学校读者我要写书评

暂无评论

Gradient-free optimization of non-differentiable hybrid neural solvers for spatially heterogeneous composites

引用

THEORETICAL AND APPLIED MECHANICS LETTERS 2025年第3期15卷

作者： Zhang, Hanfeng Luo, Tengfei Wang, Jian-Xun Univ Notre Dame Dept Aerosp & Mech Engn Notre Dame IN 46556 USA Univ Notre Dame Ctr Sustainable Energy ND Energy Notre Dame IN 46556 USA Univ Notre Dame Dept Chem & Biomol Engn Notre Dame IN 46556 USA Cornell Univ Sibley Sch Mech & Aerosp Engn Ithaca NY 14850 USA

The data-driven machine learning paradigm typically requires high-quality, large-scale datasets for training neural networks, which are often unavailable in many scientific and engineering applications. Integrating physics equations into machine learning models, either fully or partially, can mitigate these data requirements and improve generalizability;however, such approaches frequently rely on differentiable programming frameworks. This ability poses significant challenges when legacy or commercial numerical solvers, which are often non-differentiable and difficult to modify without introducing code changes, are integrated. This work addresses these challenges by leveraging the mini-batching iterative ensemble Kalman inversion (EKI) algorithm as a gradient-free training framework for hybrid neural models. The use of stochastic mini-batching significantly enhances the computational efficiency and convergence of EKI, making it well-suited for high-dimensional learning problems. The proposed method is demonstrated for modeling a fiber-reinforced composite plate, where heterogeneous local constitutive laws are parameterized by a trainable neural network embedded within the FEniCS finite element solver. Using the displacement field as indirect data, the hybrid neural FEM solver successfully predicts deformations by learning the local constitutive laws, even for unseen fiber volume fraction distributions and varying test loading conditions. These results demonstrate the effectiveness of iterative EKI in training hybrid neural models with non-differentiable components, paving the way for broader adoption of hybrid neural models in scientific and engineering applications.

关键词： Hybrid neural models Iterative Kalman inversion Scientific machine learning differentiable programming Fiber-reinforced composites

来源：评论

学校读者我要写书评

暂无评论

Clustering by sparse orthogonal NMF and interpretable neural network

引用

MULTIMEDIA SYSTEMS 2023年第6期29卷 3341-3356页

作者： Gai, Yongwei Liu, Jinglei Yantai Univ Sch Comp & Control Engn Yantai 264005 Shandong Peoples R China

Employing differentiable reconstruction to interpret the clustering layers of neural networks presents a potent solution to the interpretability challenges encountered when applying neural networks within the multimedia sector. However, most of the existing approaches proposed for interpretability of machine learning make post hoc interpretations of neural networks. While existing approaches have made progress in post hoc interpretation, they still fall short in providing clear explanations for black-box models. There are two main challenges: the first is how we should design an interpretable neural network using sparse orthogonal non-negative matrix factorization (NMF) instead of performing post hoc interpretation. The second is how to implement sparse orthogonal NMF and perform clustering using the designed neural network. To solve these two problems, we address this issue by designing a New Interpretable Neural Network (NINN) that uses sparse orthogonal NMF as a basis for its architecture. We innovate in three aspects: first, NINN is a transparent neural network model with greater interpretability in the clustering layer. Second, NINN automatically performs gradient-based optimization of the parameters in the program and has the advantage of end-to-end learning. Third, since NINN is a differentiable reformulation of sparse orthogonal NMF, NINN inherits many properties of both NMF and neural networks, such as parallel solving, online clustering, dimensionality reduction, and unsupervised learning. Experimental evidence demonstrates that the NINN outperforms a myriad of conventional clustering algorithms, such as k-means and NMF, as well as some of the latest models, in terms of clustering performance.

关键词： differentiable programming Interpretability Neural clustering Sparse orthogonal NMF Transparent neural networks

来源：评论

学校读者我要写书评

暂无评论

Temporal Set Inversion for Animated Implicits

引用

ACM TRANSACTIONS ON GRAPHICS 2023年第4期42卷 1-18页

作者： Jazar, Kavosh Kry, Paul G. McGill Univ Montreal PQ Canada

We exploit the temporal coherence of closed-form animated implicit surfaces by locally re-evaluating an octree-like discretization of the implicit field only as and where is necessary to rigorously maintain a global error invariant over time, thereby saving resources in static or slowly-evolving areas far from the motion where per-frame updates are not necessary. We treat implicit surface rendering as a special case of the continuous constraint satisfaction problem of set inversion, which seeks preimages of arbitrary sets under vector-valued functions. From this perspective, we formalize a temporally-coherent set inversion algorithm that localizes changes in the field by range-bounding its time derivatives using interval arithmetic. We implement our algorithm on the GPU using persistent thread scheduling and apply it to the scalar case of implicit surface and swept volume rendering where we achieve significant speedups in complex scenes with localized deformations like those found in games and modelling applications where interactivity is required and bounded-error approximation is acceptable.

关键词： implicit surface signed distance field sdf temporal coherence sparse voxel octree root-finding branch-and-bound global optimization nonlinear optimization constraint satisfaction error analysis subpaving subdivision isosurface differentiable programming

来源：评论

学校读者我要写书评

暂无评论

A differentiable Perspective for Multi-View Spectral Clustering With Flexible Extension

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第6期45卷 7087-7098页

作者： Lu, Zhoumin Nie, Feiping Wang, Rong Li, Xuelong Northwestern Polytech Univ Sch Comp Sci Sch Artificial Intelligence Key Lab Intelligent Interact & ApplicatOPt & Elec Xian 710072 Peoples R China Northwestern Polytech Univ Sch Artificial Intelligence Key Lab Intelligent Interact & Applicat OPt & Elect iOPENMinist Ind & Informat Technol Xian 710072 Peoples R China

Multi-view clustering aims to discover common patterns from multi-source data, whose generality is remarkable. Compared with traditional methods, deep learning methods are data-driven and have a larger search space for solutions, which may find a better solution to the problem. In addition, more considerations can be introduced by loss functions, so deep models are highly reusable. However, compared with deep learning methods, traditional methods have better interpretability, whose optimization is relatively stable. In this paper, we propose a multi-view spectral clustering model, combining the advantages of traditional methods and deep learning methods. Specifically, we start with the objective function of traditional spectral clustering, perform multi-view extension, and then obtain the traditional optimization process. By partially parameterizing this process, we further design corresponding differentiable modules, and finally construct a complete network structure. The model is interpretable and extensible to a certain extent. Experiments show that the model performs better than other multi-view clustering algorithms, and its semi-supervised classification extension also has excellent performance compared to other algorithms. Further experiments also show the stability and fewer iterations of the model training.

关键词： Deep learning Kernel Clustering algorithms Optimization Neural networks Training Visualization Multi-view learning spectral clustering semi-supervised classification flexible extension differentiable programming

来源：评论

学校读者我要写书评

暂无评论

Deep Time Series Forecasting With Shape and Temporal Criteria

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第1期45卷 342-355页

作者： Le Guen, Vincent Thome, Nicolas EDF Rech & Dev Site Chatou PRISME F-78400 Chatou France Conservatoire Natl Arts & Metiers CEDRIC F-75003 Paris France

This paper addresses the problem of multi-step time series forecasting for non-stationary signals that can present sudden changes. Current state-of-the-art deep learning forecasting methods, often trained with variants of the MSE, lack the ability to provide sharp predictions in deterministic and probabilistic contexts. To handle these challenges, we propose to incorporate shape and temporal criteria in the training objective of deep models. We define shape and temporal similarities and dissimilarities, based on a smooth relaxation of Dynamic Time Warping (DTW) and Temporal Distortion Index (TDI), that enable to build differentiable loss functions and positive semi-definite (PSD) kernels. With these tools, we introduce DILATE (DIstortion Loss including shApe and TimE), a new objective for deterministic forecasting, that explicitly incorporates two terms supporting precise shape and temporal change detection. For probabilistic forecasting, we introduce STRIPE++ (Shape and Time diverRsIty in Probabilistic for Ecasting), a framework for providing a set of sharp and diverse forecasts, where the structured shape and time diversity is enforced with a determinantal point process (DPP) diversity loss. Extensive experiments and ablations studies on synthetic and real-world datasets confirm the benefits of leveraging shape and time features in time series forecasting.

关键词： Forecasting Shape Probabilistic logic Time series analysis Predictive models Training Kernel Time series forecasting deep neural networks differentiable programming loss functions structured prediction shape and temporal criteria dynamic time warping time distortion structured diversity determinantal point processes

来源：评论

学校读者我要写书评

暂无评论

CalcGraph: taming the high costs of deep learning using models

引用

SOFTWARE AND SYSTEMS MODELING 2023年第4期22卷 1151-1174页

作者： Lorentz, Joe Hartmann, Thomas Moawad, Assaad Fouquet, Francois Aouada, Djamila Le Traon, Yves DataThings SA 5 Rue Ind L-1811 Luxembourg Luxembourg Univ Luxembourg Campus Kirchberg6 Rue Richard Coudenhove Kalergi L-1359 Luxembourg Luxembourg

Models based on differential programming, like deep neural networks, are well established in research and able to outperform manually coded counterparts in many applications. Today, there is a rising interest to introduce this flexible modeling to solve real-world problems. A major challenge when moving from research to application is the strict constraints on computational resources (memory and time). It is difficult to determine and contain the resource requirements of differential models, especially during the early training and hyperparameter exploration stages. In this article, we address this challenge by introducing CalcGraph, a model abstraction of differentiable programming layers. CalcGraph allows to model the computational resources that should be used and then CalcGraph's model interpreter can automatically schedule the execution respecting the specifications made. We propose a novel way to efficiently switch models from storage to preallocated memory zones and vice versa to maximize the number of model executions given the available resources. We demonstrate the efficiency of our approach by showing that it consumes less resources than state-of-the-art frameworks like TensorFlow and PyTorch for single-model and multi-model execution.

关键词： differentiable programming Computational graph model Edge AI

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：