It is shown that over-parameterized neural networks can achieve minimax optimal rates of convergence (up to logarithmic factors) for learning functions from certain smooth function classes, if the weights are suitably constrained or regularized. Specifically, we consider the nonparametric regression of estimating an unknown $d$-variate function by using shallow ReLU neural networks. It is assumed that the regression function is from the H\"older space with smoothness $\alpha<(d+3)/2$ or a variation space corresponding to shallow neural networks, which can be viewed as an infinitely wide neural network. In this setting, we prove that least squares estimators based on shallow neural networks with certain norm constraints on the weights are minimax optimal, if the network width is sufficiently large. As a byproduct, we derive a new size-independent bound for the local Rademacher complexity of shallow ReLU neural networks, which may be of independent interest.
相關內容
神經網絡（Neural Networks）是世界上三個最古老的神經建模學會的檔案期刊:國際神經網絡學會(INNS)、歐洲神經網絡學會(ENNS)和日本神經網絡學會(JNNS)。神經網絡提供了一個論壇，以發展和培育一個國際社會的學者和實踐者感興趣的所有方面的神經網絡和相關方法的計算智能。神經網絡歡迎高質量論文的提交，有助于全面的神經網絡研究，從行為和大腦建模，學習算法，通過數學和計算分析，系統的工程和技術應用，大量使用神經網絡的概念和技術。這一獨特而廣泛的范圍促進了生物和技術研究之間的思想交流，并有助于促進對生物啟發的計算智能感興趣的跨學科社區的發展。因此，神經網絡編委會代表的專家領域包括心理學，神經生物學，計算機科學，工程，數學，物理。該雜志發表文章、信件和評論以及給編輯的信件、社論、時事、軟件調查和專利信息。文章發表在五個部分之一:認知科學，神經科學，學習系統，數學和計算分析、工程和應用。
官網地址：
Building a multi-modality multi-task neural network toward accurate and robust performance is a de-facto standard in perception task of autonomous driving. However, leveraging such data from multiple sensors to jointly optimize the prediction and planning tasks remains largely unexplored. In this paper, we present FusionAD, to the best of our knowledge, the first unified framework that fuse the information from two most critical sensors, camera and LiDAR, goes beyond perception task. Concretely, we first build a transformer based multi-modality fusion network to effectively produce fusion based features. In constrast to camera-based end-to-end method UniAD, we then establish a fusion aided modality-aware prediction and status-aware planning modules, dubbed FMSPnP that take advantages of multi-modality features. We conduct extensive experiments on commonly used benchmark nuScenes dataset, our FusionAD achieves state-of-the-art performance and surpassing baselines on average 15% on perception tasks like detection and tracking, 10% on occupancy prediction accuracy, reducing prediction error from 0.708 to 0.389 in ADE score and reduces the collision rate from 0.31% to only 0.12%.
In a variety of application areas, there is interest in assessing evidence of differences in the intensity of event realizations between groups. For example, in cancer genomic studies collecting data on rare variants, the focus is on assessing whether and how the variant profile changes with the disease subtype. Motivated by this application, we develop multiresolution nonparametric Bayes tests for differential mutation rates across groups. The multiresolution approach yields fast and accurate detection of spatial clusters of rare variants, and our nonparametric Bayes framework provides great flexibility for modeling the intensities of rare variants. Some theoretical properties are also assessed, including weak consistency of our Dirichlet Process-Poisson-Gamma mixture over multiple resolutions. Simulation studies illustrate excellent small sample properties relative to competitors, and we apply the method to detect rare variants related to common variable immunodeficiency from whole exome sequencing data on 215 patients and over 60,027 control subjects.
Neural network pruning is a highly effective technique aimed at reducing the computational and memory demands of large neural networks. In this research paper, we present a novel approach to pruning neural networks utilizing Bayesian inference, which can seamlessly integrate into the training procedure. Our proposed method leverages the posterior probabilities of the neural network prior to and following pruning, enabling the calculation of Bayes factors. The calculated Bayes factors guide the iterative pruning. Through comprehensive evaluations conducted on multiple benchmarks, we demonstrate that our method achieves desired levels of sparsity while maintaining competitive accuracy.
To understand the ability and limitations of convolutional neural networks to generate time series that mimic complex temporal signals, we trained a generative adversarial network consisting of deep convolutional networks to generate chaotic time series and used nonlinear time series analysis to evaluate the generated time series. A numerical measure of determinism and the Lyapunov exponent, a measure of trajectory instability, showed that the generated time series well reproduce the chaotic properties of the original time series. However, error distribution analyses showed that large errors appeared at a low but non-negligible rate. Such errors would not be expected if the distribution were assumed to be exponential.
In the future, it is anticipated that software-defined networking (SDN) will become the preferred platform for deploying diverse networks. Compared to traditional networks, SDN separates the control and data planes for efficient domain-wide traffic routing and management. The controllers in the control plane are responsible for programming data plane forwarding devices, while the top layer, the application plane, enforces policies and programs the network. The different levels of the SDN use interfaces for communication. However, SDN faces challenges with traffic distribution, such as load imbalance, which can negatively affect the network performance. Consequently, developers have developed various SDN load-balancing solutions to enhance SDN effectiveness. In addition, researchers are considering the potential of implementing some artificial intelligence (AI) approaches into SDN to improve network resource usage and overall performance due to the fast growth of the AI field. This survey focuses on the following: Firstly, analyzing the SDN architecture and investigating the problem of load balancing in SDN. Secondly, categorizing AI-based load balancing methods and thoroughly assessing these mechanisms from various perspectives, such as the algorithm/technique employed, the tackled problem, and their strengths and weaknesses. Thirdly, summarizing the metrics utilized to measure the effectiveness of these techniques. Finally, identifying the trends and challenges of AI-based load balancing for future research.
Determining the memory capacity of two-layer neural networks with m hidden neurons and input dimension d (i.e., md+m total trainable parameters), which refers to the largest size of general data the network can memorize, is a fundamental machine-learning question. For non-polynomial real analytic activation functions, such as sigmoids and smoothed rectified linear units (smoothed ReLUs), we establish a lower bound of md/2 and optimality up to a factor of approximately 2. Analogous prior results were limited to Heaviside and ReLU activations, with results for smooth activations suffering from logarithmic factors and requiring random data. To analyze the memory capacity, we examine the rank of the network's Jacobian by computing the rank of matrices involving both Hadamard powers and the Khati-Rao product. Our computation extends classical linear algebraic facts about the rank of Hadamard powers. Overall, our approach differs from previous works on memory capacity and holds promise for extending to deeper models and other architectures.
The single-letter characterization of the entanglement-assisted capacity of a quantum channel is one of the seminal results of quantum information theory. In this paper, we consider a modified communication scenario in which the receiver is allowed an additional, `inconclusive' measurement outcome, and we employ an error metric given by the error probability in decoding the transmitted message conditioned on a conclusive measurement result. We call this setting postselected communication and the ensuing highest achievable rates the postselected capacities. Here, we provide a precise single-letter characterisation of postselected capacities in the setting of entanglement assistance as well as the more general non-signalling assistance, establishing that they are both equal to the channel's projective mutual information -- a variant of mutual information based on the Hilbert projective metric. We do so by establishing bounds on the one-shot postselected capacities, with a lower bound that makes use of a postselected teleportation protocol and an upper bound in terms of the postselected hypothesis testing relative entropy. As such, we obtain fundamental limits on a channel's ability to communicate even when this strong resource of postselection is allowed, implying limitations on communication even when the receiver has access to postselected closed timelike curves.
Designing scalable estimation algorithms is a core challenge in modern statistics. Here we introduce a framework to address this challenge based on parallel approximants, which yields estimators with provable properties that operate on the entirety of very large, distributed data sets. We first formalize the class of statistics which admit straightforward calculation in distributed environments through independent parallelization. We then show how to use such statistics to approximate arbitrary functional operators in appropriate spaces, yielding a general estimation framework that does not require data to reside entirely in memory. We characterize the $L^2$ approximation properties of our approach and provide fully implemented examples of sample quantile calculation and local polynomial regression in a distributed computing environment. A variety of avenues and extensions remain open for future work.
Recently, graph neural networks have been gaining a lot of attention to simulate dynamical systems due to their inductive nature leading to zero-shot generalizability. Similarly, physics-informed inductive biases in deep-learning frameworks have been shown to give superior performance in learning the dynamics of physical systems. There is a growing volume of literature that attempts to combine these two approaches. Here, we evaluate the performance of thirteen different graph neural networks, namely, Hamiltonian and Lagrangian graph neural networks, graph neural ODE, and their variants with explicit constraints and different architectures. We briefly explain the theoretical formulation highlighting the similarities and differences in the inductive biases and graph architecture of these systems. We evaluate these models on spring, pendulum, gravitational, and 3D deformable solid systems to compare the performance in terms of rollout error, conserved quantities such as energy and momentum, and generalizability to unseen system sizes. Our study demonstrates that GNNs with additional inductive biases, such as explicit constraints and decoupling of kinetic and potential energies, exhibit significantly enhanced performance. Further, all the physics-informed GNNs exhibit zero-shot generalizability to system sizes an order of magnitude larger than the training system, thus providing a promising route to simulate large-scale realistic systems.
Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of these models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism, which prevents the model from obtaining adequate global information. In order to increase the receptive field, we propose a novel deep Hierarchical Graph Convolutional Network (H-GCN) for semi-supervised node classification. H-GCN first repeatedly aggregates structurally similar nodes to hyper-nodes and then refines the coarsened graph to the original to restore the representation for each node. Instead of merely aggregating one- or two-hop neighborhood information, the proposed coarsening procedure enlarges the receptive field for each node, hence more global information can be learned. Comprehensive experiments conducted on public datasets demonstrate the effectiveness of the proposed method over the state-of-art methods. Notably, our model gains substantial improvements when only a few labeled samples are provided.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191