Results 21 to 30 of about 48,655 (264)
Generative Moment Matching Networks
CoRR, 2015 We consider the problem of learning deep generative models from data. We formulate a method that generates an independent sample via a single feedforward pass through a multilayer perceptron, as in the recently proposed generative adversarial networks (Goodfellow et al., 2014).
Yujia Li 0001 +2 more
openaire +3 more sources
Registration of visual-infrared images based on ellipse symmetrical orientation moment
工程科学学报, 2017 For addressing the difficulties in the registration of multimodal images in image-matching guidance, a new visualinfrared image-registration approach based on ellipse symmetrical orientation moment was proposed.
CHEN Shi-wei +3 more
doaj +1 more source
Enhanced XUV Harmonics Generation with an Intense Laser Field in the Overdriven Regime
Photonics, 2023 High-order harmonic generation with high photon flux has been a challenging task in strong-field physics. According to the high-order harmonic generation process, the essential requirements for achieving efficient harmonic radiations inside a gas medium ...
Zhiyong Qin +8 more
doaj +1 more source
Gramian Preserving Moment Matching for Linear Systems*
2023 European Control Conference (ECC), 2023 Time-domain moment matching-based model order reduction is an efficient technique that provides a family of parametrized reduced order models with identical moments evaluated in a set of points. The free parameters provide flexibility to impose additional constraints such as stability, passivity, and derivative matching.
Yu Kawano +2 more
openaire +2 more sources
Indirect Inference: Which Moments to Match?
Econometrics, 2019 The standard approach to indirect inference estimation considers that the auxiliary parameters, which carry the identifying information about the structural parameters of interest, are obtained from some recently identified vector of estimating equations.
David T. Frazier, Eric Renault
doaj +1 more source
Moment Matching by Kernel-Based Learning [PDF]
IEEE Transactions on Automatic ControlIn this article, we introduce a kernel-based moment matching theory that relies upon a novel data-driven model reduction method, employing the estimation of moments within a reproducing kernel Hilbert space. We demonstrate that moment estimation can be enhanced by appropriately tuning the regularization term, regardless of the kernel choice.
Alessio Moreschini +3 more
openaire +4 more sources
Joint Image Deblurring and Matching with Blurred Invariant-Based Sparse Representation Prior
Complexity, 2019 Image matching is important for vision-based navigation. However, most image matching approaches do not consider the degradation of the real world, such as image blur; thus, the performance of image matching often decreases greatly. Recent methods try to
Yuanjie Shao +3 more
doaj +1 more source
Dynamic model reduction: An overview of available techniques with application to power systems [PDF]
Serbian Journal of Electrical Engineering, 2012 This paper summarises the model reduction techniques used for the reduction of large-scale linear and nonlinear dynamic models, described by the differential and algebraic equations that are commonly used in control theory. The groups of methods
Đukić Savo D., Sarić Andrija T.
doaj +1 more source
CoRRDiffusion models and Flow Matching generate high-quality samples but are slow at inference, and distilling them into few-step models often leads to instability and extensive tuning. To resolve these trade-offs, we propose Inductive Moment Matching (IMM), a new class of generative models for one- or few-step sampling with a single-stage training ...
Linqi Zhou, Stefano Ermon, Jiaming Song
openaire +3 more sources
Moment-Matching and Best Entropy Estimation
Journal of Mathematical Analysis and Applications, 1994 General conditions ensuring uniform convergence of the best entropy estimates to the unknown function are given. Simple approximation theoretic arguments to moment-matching procedure enables one to deduce uniform convergence from interpolation properties of the estimates.
Borwein, P., Lewis, A.S.
openaire +2 more sources