Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

237474711948 · Jun 202019922001200920182026
48 results for Haar scattering networks

Haar scattering networks improve pattern recognition across various tasks.

problem Improving pattern recognition in diverse tasks like regression and classification.
method Stacking convolutional filters based on Haar wavelets followed by non-linear operators.
result Outperformed best algorithms in 4 out of 18 data classification problems.

In this article we propose building general-purpose function approximators on top of Haar Scattering Networks. We advocate that this architecture enables a better comprehension of feature extraction, in addition to its implementation simplicity and low computational costs. We show its approximation and feature extracti…

2018-04-09abs ↗pdf ↗

New MHSNs extract multiscale features from complex data for robust classification.

problem Signal classification and domain classification on complex data.
method Layered structure with multiscale basis dictionaries, pooling operations, and invariant features.
result High-accuracy classification with fewer parameters than traditional graph neural networks.

Novel Haar-Laplacian for directed graphs enhances spectral graph applications.

problem Lack of suitable Laplacian for directed graphs in spectral graph theory.
method Inspired by Haar-like transformation, introduces a Hermitian matrix preserving direction and weight.
result HaarNet outperforms in weight prediction and denoising on directed graphs.

This work proves the asymptotic freeness of layerwise Jacobians in MLPs with Haar orthogonal matrices.

problem Proving the asymptotic freeness of layerwise Jacobians in multilayer perceptrons (MLPs).
method Replacing each layer's parameter matrix with itself multiplied by a Haar orthogonal matrix, and using the invariance of the MLP.
result Proves the asymptotic freeness of layerwise Jacobians in MLPs with Haar orthogonal matrices.

Unified graph scattering transforms improve theoretical properties of graph neural networks.

problem Improving theoretical guarantees for graph neural networks.
method Introducing windowed and non-windowed geometric scattering transforms for graphs.
result Unified family of graph scattering transforms with provable stability and invariance.

Quantum neural networks converge to Gaussian processes as they grow.

problem Understanding the convergence of quantum neural networks to Gaussian processes.
method Analyzing Haar random unitary and orthogonal deep QNNs, considering input states, measurement observables, and non-independence of unitary matrix entries.
result Quantum neural networks outputs converge to Gaussian processes in the limit of large Hilbert space dimension.

Geometric wavelet scattering on manifolds improves neural network understanding.

problem Improving neural network understanding on manifold and graph domains.
method Defining a geometric scattering transform based on wavelet filters and nonlinearities.
result Generalizes deformation stability and local translation invariance to manifolds.

Graph scattering transforms are stable to metric perturbations of network topology.

problem Stability of graph data representations under metric perturbations.
method Extending scattering transforms to network data using multiresolution graph wavelets and graph convolutions.
result Graph scattering transforms are stable to metric perturbations of the underlying network topology.

We introduce general scattering transforms as mathematical models of deep neural networks with l2 pooling. Scattering networks iteratively apply complex valued unitary operators, and the pooling is performed by a complex modulus. An expected scattering defines a contractive representation of a high-dimensional probabil…

2013-06-24abs ↗pdf ↗

Scattering networks improve image representation learning without deep learning.

problem Improving image representation learning without deep learning.
method Scattering networks as generic representations in scattering space.
result Scattering networks achieve competitive results in supervised and unsupervised learning.

Scattering networks maximize separation on low-dimensional data.

problem Maximizing separation capacity on low-dimensional datasets.
method Characterize and bound separation capacity for feature extractors, then apply to scattering networks with specific criteria.
result Design criteria for scattering networks to maximize separation on low-dimensional data.

A deep network classifies images by scattering and dictionary learning.

problem Classifying images with high accuracy using deep learning.
method Sparse scattering transform followed by 1\ell^1 dictionary learning in a deep convolutional network.
result Higher classification accuracy than AlexNet on ImageNet dataset.

Paper interprets deep learning using decision trees and Haar wavelets.

problem Understanding the function approximation capabilities of ReLU deep learning.
method Constructing a deep learning structure equivalent to a forest and approximating Haar wavelet functions with ReLU deep learning.
result ReLU deep learning can be considered as decision trees and approximates Haar wavelet functions with arbitrary precision.

Deep learning solves wave-based inverse problems, including super-resolution imaging.

problem Solving inverse wave scattering problems across all length scales.
method Wide-band butterfly network coupled with dynamic noise injection.
result Framework successfully solves super-resolution imaging problems.

Scattering GCN improves graph neural networks by filtering oversmoothing.

problem Oversmoothing in GCNs limits their ability to distinguish graph nodes.
method Augmenting GCNs with geometric scattering transforms and residual convolutions.
result Scattering GCN outperforms GAT in semi-supervised node classification.

This paper proposes a new methodology to compute Value at Risk (VaR) for quantifying losses in credit portfolios. We approximate the cumulative distribution of the loss function by a finite combination of Haar wavelets basis functions and calculate the coefficients of the approximation by inverting its Laplace transfor…

2009-04-29abs ↗pdf ↗

Deep neural networks correct Mie scattering in FTIR spectra of biological samples.

problem Mie scattering obscures biochemically relevant spectral information in FTIR spectra of biological samples.
method Deep neural networks to approximate the preprocessing function that removes Mie scattering.
result The model is faster and more generalizable across different tissue types.

A new GNN module learns geometric scattering features for better graph classification and feature exploration.

problem Learning long-range graph relations and extracting meaningful features from graphs.
method Proposes a learnable geometric scattering (LEGS) module in graph neural networks (GNNs), incorporating wavelet filters.
result LEGS-based GNNs outperform existing methods in graph classification and feature extraction tasks.

Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood. We compute deep convolutional network generators by inverting a fixed embedding operator. Therefore, they do not require to be o…

2018-05-17abs ↗pdf ↗

New deep learning model estimates scattering timescale of FRBs efficiently.

problem Estimating scattering timescale of fast radio bursts (FRBs) is a bottleneck.
method Multimodal Transformer Based Generic Mixture Density Network (MT-GMDN) that ingests dynamic spectrum and timeseries profile.
result Achieves 94% R2R^2 on expected value of ττ for measurable scattering.

Geometric scattering for graph data enhances feature retention and classification.

problem Tackling the generalization of scattering transforms to graph data.
method Analogous to ConvNets, we develop geometric scattering for graph data, focusing on feature stability under graph deformations.
result Extracted features retain informative variability and relations in graph data, aiding classification and exploration.

FAT-GAN simulates electron-proton scattering without theoretical assumptions.

problem Efficiently training GANs to simulate complex particle distributions.
method Developed FAT-GAN using transformed and augmented features to improve GAN performance.
result FAT-GAN accurately reproduces electron momenta distributions in electron-proton scattering.

Deep neural networks' Jacobian spectrum becomes well-conditioned with orthogonal weights.

problem Understanding and handling the Jacobian spectrum of deep neural networks.
method Applying free probability theory to show almost sure asymptotic freeness of Jacobians in the wide limit.
result Layer-wise Jacobians of deep neural networks with orthogonal weights are almost surely asymptotically free.

A new hybrid GNN framework tackles oversmoothing in graph data.

problem Oversmoothing in graph convolutional networks limits their expressive power and generalization.
method Combines traditional GCN filters with band-pass filters defined via geometric scattering and introduces an attention framework.
result Improves expressive power and generalization of graph convolutional networks.

New method uses GANs and proper scoring rules for robust scatter estimation.

problem Robust scatter estimation in statistics.
method General learning via classification framework based on proper scoring rules.
result Proposed robust scatter estimators achieve minimax rate under Huber's contamination model.

A scattering transform defines a signal representation which is invariant to translations and Lipschitz continuous relatively to deformations. It is implemented with a non-linear convolution network that iterates over wavelet and modulus operators. Lipschitz continuity locally linearizes deformations. Complex classes o…

2011-12-05abs ↗pdf ↗

Predict cell loads in cellular networks using statistical learning of geometric marks.

problem Predicting cell loads in cellular networks using geometric marks.
method Statistical regression model and scattering moments of random measures.
result Scattering moments can capture similar geometry information as baseline approach and improve performance.

Transfer learning improves lensless imaging through scattering media with fewer samples.

problem Training deep neural networks (DNNs) for lensless imaging through scattering media requires large datasets, leading to poor cross-dataset performance.
method Proposed transfer learning approach using LISMU-FCN and LISMU-OCN architectures with a balance loss function.
result Transfer learning enables imaging across similar and significantly different datasets with fewer samples.