One or Two Components? The Scattering Transform Answers

• URL: http://arxiv.org/abs/2003.01037v2
• Date: Thu, 25 Jun 2020 10:51:12 GMT
• Title: One or Two Components? The Scattering Transform Answers
• Abstract summary: We show that renormalizing second-order nodes by their first-order parents gives a simple numerical criterion to assess whether two neighboring components will interfere psychoacoustically. We generalize the "one or two components" framework to three sine waves or more, and prove that the effective scattering depth of a Fourier series grows in logarithmic proportion to its bandwidth.
• Score: 17.026628650481168
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the aim of constructing a biologically plausible model of machine listening, we study the representation of a multicomponent stationary signal by a wavelet scattering network. First, we show that renormalizing second-order nodes by their first-order parents gives a simple numerical criterion to assess whether two neighboring components will interfere psychoacoustically. Secondly, we run a manifold learning algorithm (Isomap) on scattering coefficients to visualize the similarity space underlying parametric additive synthesis. Thirdly, we generalize the "one or two components" framework to three sine waves or more, and prove that the effective scattering depth of a Fourier series grows in logarithmic proportion to its bandwidth.

Related papers

• Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks [64.7580803923092]
  We prove the first algorithmic separation between constant-depth and logarithmic-depth networks.<n>Specifically, we identify a class of Boolean functions with hierarchically structured spectra that logarithmic-depth networks can learn efficiently.
  arXiv  Detail & Related papers  (2026-07-28T02:13:30Z)
• Directed Graph Topology Inference via Graph Filter Identification [54.541275287889164]
  We address the problem of inferring a directed network from nodal measurements generated by a graph convolutional filter.<n>A joint graph filter and topology identification algorithm is also proposed, which alternates between the aforementioned steps to offer improved sample complexity.
  arXiv  Detail & Related papers  (2026-06-25T18:25:57Z)
• Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification [52.517763621139956]
  3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis.<n>Standard adaptive density control relies on screen-space positional gradients.<n>We present a structure-aware densification framework for 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-04-30T15:37:20Z)
• On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking [49.1352577985191]
  We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task.<n>Our work provides a full mechanistic interpretation of the learned model and a theoretical explanation of its training dynamics.
  arXiv  Detail & Related papers  (2026-02-18T20:25:13Z)
• Subtractive Modulative Network with Learnable Periodic Activations [59.89799070130572]
  We propose a novel, parameter-efficient Implicit Neural Representation architecture inspired by classical subtractive synthesis.<n>Our SMN achieves a PSNR of $40+$ dB on two image datasets, comparing favorably against state-of-the-art methods in terms of both reconstruction accuracy and parameter efficiency.
  arXiv  Detail & Related papers  (2026-02-18T10:20:50Z)
• SWAN: Self-supervised Wavelet Neural Network for Hyperspectral Image Unmixing [0.2624902795082451]
  We present SWAN: a three-stage, self-supervised wavelet neural network for estimation of endmembers and abundances from hyperspectral imagery.<n>The idea is to exploit latent symmetries from thus obtained invariant and covariant features using a self-supervised learning paradigm.<n> Experiments are conducted on two benchmark synthetic data sets with different signal-to-noise ratios as well as on three real benchmark hyperspectral data sets.
  arXiv  Detail & Related papers  (2025-10-26T10:05:48Z)
• Different Phases in a Dissipative Rydberg Lattice : Roles of Occupancy and On-site Interaction [0.0]
  We study a two-level dissipative non-equilibrium bosonic Rydberg system in an optical lattice.<n>It is found that, depending on the on-site interaction strength, the system can either be uniform or have an antiferromagnet-like density-wave structure.<n>It is observed that an initial population difference across the sublattices helps to enhance the density-wave order.
  arXiv  Detail & Related papers  (2025-09-09T09:03:00Z)
• Second-Order Tensorial Partial Differential Equations on Graphs [13.421159402806675]
  We introduce second-order tensorial partial differential equations on graphs (SoTPDEG)<n>We propose the first theoretically grounded framework for second-order continuous product graph neural networks (GNNs)
  arXiv  Detail & Related papers  (2025-09-02T07:01:20Z)
• Dual Signal Decomposition of Stochastic Time Series [0.0]
  The decomposition is performed by applying machine learning techniques to fit the dual signal.<n>The proposed decomposition can be applied as a smoothing algorithm against the mean and dispersion of the time series.<n>The dual signal can be represented on the 2D space and used to learn inherent structures, to forecast both mean and dispersion, or to analyze cross effects in case of multiple time series.
  arXiv  Detail & Related papers  (2025-08-08T00:30:41Z)
• Noisy Cyclic Quantum Random Walk [0.0]
  We explore static noise in a discrete quantum random walk over a homogeneous cyclic graph. We control the spectral properties of the noiseless step operator on the unit circle in the complex plane. We observe a transition from super-diffusive to sub-diffusive behavior for uniformly distributed noise.
  arXiv  Detail & Related papers  (2024-11-30T17:02:38Z)
• WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration [68.25711405944239]
  Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. We introduce a model-driven WiNet that incrementally estimates scale-wise wavelet coefficients for the displacement/velocity field across various scales.
  arXiv  Detail & Related papers  (2024-07-18T11:51:01Z)
• Three-body Forces in Oscillator Bases Expansion [0.0]
  The method is generalised to include the management of a given class of three-body forces. The accuracy of the generalisation is assessed by comparing with results from Lagrange mesh method. Extensions for systems of $N$ identical bodies and for systems of two identical particles and one distinct are also discussed.
  arXiv  Detail & Related papers  (2024-05-28T13:50:20Z)
• Generating Graphs via Spectral Diffusion [48.70458395826864]
  We present GGSD, a novel graph generative model based on 1) the spectral decomposition of the graph Laplacian matrix and 2) a diffusion process. An extensive set of experiments on both synthetic and real-world graphs demonstrates the strengths of our model against state-of-the-art alternatives.
  arXiv  Detail & Related papers  (2024-02-29T09:26:46Z)
• Generative Adversarial Networks to infer velocity components in rotating turbulent flows [2.0873604996221946]
  We show that CNN and GAN always outperform EPOD both concerning point-wise and statistical reconstructions. The analysis is performed using both standard validation tools based on $L$ spatial distance between the prediction and the ground truth.
  arXiv  Detail & Related papers  (2023-01-18T13:59:01Z)
• Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction [120.08257447708503]
  Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction. We propose a novel skeleton-parted graph scattering network (SPGSN) SPGSN outperforms state-of-the-art methods by remarkable margins of 13.8%, 9.3% and 2.7% in terms of 3D mean per joint position error (MPJPE) on Human3.6M, CMU Mocap and 3DPW datasets, respectively.
  arXiv  Detail & Related papers  (2022-07-31T05:51:39Z)
• Blind Extraction of Equitable Partitions from Graph Signals [0.0]
  We study a blind identification problem in which we aim to recover an equitable partition of a network without the knowledge of the network's edges. We present a simple spectral algorithm to extract the relevant equitable partitions.
  arXiv  Detail & Related papers  (2022-03-10T15:03:32Z)
• Spectral embedding and the latent geometry of multipartite networks [67.56499794542228]
  Many networks are multipartite, meaning their nodes can be divided into partitions and nodes of the same partition are never connected. This paper demonstrates that the node representations obtained via spectral embedding live near partition-specific low-dimensional subspaces of a higher-dimensional ambient space. We propose a follow-on step after spectral embedding, to recover node representations in their intrinsic rather than ambient dimension.
  arXiv  Detail & Related papers  (2022-02-08T15:52:03Z)
• Seeing Implicit Neural Representations as Fourier Series [13.216389226310987]
  Implicit Neural Representations (INR) use multilayer perceptrons to represent high-frequency functions in low-dimensional problem domains. These representations achieved state-of-the-art results on tasks related to complex 3D objects and scenes. This work analyzes the connection between the two methods and shows that a Fourier mapped perceptron is structurally like one hidden layer SIREN.
  arXiv  Detail & Related papers  (2021-09-01T08:40:20Z)
• Quantum asymmetry and noisy multi-mode interferometry [55.41644538483948]
  Quantum asymmetry is a physical resource which coincides with the amount of coherence between the eigenspaces of a generator. We show that the asymmetry may emphincrease as a result of a emphdecrease of coherence inside a degenerate subspace.
  arXiv  Detail & Related papers  (2021-07-23T07:30:57Z)
• Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection [54.98042023365694]
  We propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples. The proposed model consists of two sub-models parameterized by neural networks.
  arXiv  Detail & Related papers  (2020-07-23T18:47:36Z)
• Manifold-Aware CycleGAN for High-Resolution Structural-to-DTI Synthesis [8.829738147738222]
  We propose a manifold-aware CycleGAN that learns the generation of high-resolution DTI from unpaired T1w images. Our method is able to generate realistic high-resolution DTI that can be used to compute diffusion-based metrics and potentially run fiber tractography algorithms.
  arXiv  Detail & Related papers  (2020-04-01T00:08:14Z)
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees [106.91654068632882]
  We consider the bipartite graph and formalize its representation learning problem as a statistical estimation problem of parameters in a semiparametric exponential family distribution. We show that the proposed objective is strongly convex in a neighborhood around the ground truth, so that a gradient descent-based method achieves linear convergence rate. Our estimator is robust to any model misspecification within the exponential family, which is validated in extensive experiments.
  arXiv  Detail & Related papers  (2020-03-02T16:40:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.