We describe convolutional networks using harmonic functions.
problem Understanding the function space and smoothness of convolutional networks.
method Using reproducing kernel Hilbert spaces and functional ANOVA decomposition.
result Convolutional networks can be decomposed into a sum of elementary functions.
GCNs improve regression tasks by aggregating neighbor signals.
problem GCNs' statistical properties in regression tasks are poorly understood.
method Examined two GCN convolutions and their impact on learning error.
result GCNs have a bias-variance trade-off that depends on neighborhood size and topology.
Convolutional neural networks learn effective summary statistics for ABC inference.
problem Selecting high-quality summary statistics for accurate ABC inference in complex systems.
method Proposes a CNN architecture to automatically learn informative summary statistics from time series data.
result CNNs can effectively circumvent the statistics selection problem in ABC inference.
Proposes a new normalization method using convolutional neural networks.
problem Slow and inefficient training of deep neural networks.
method Uses depth-wise convolutional neural networks to approximate statistics.
result Learned coefficients improve the approximation of statistics.
New bounds for quantile aggregation unify and clarify existing methods.
problem Analytical bounds for quantile aggregation with dependence uncertainty.
method Using inf-convolution of quantile-based risk measures, establish new analytical bounds called convolution bounds.
result Convolution bounds are the best available and provide sharp results in many cases.
Proposes LC-ST-FCN for better ride-sourcing demand forecasting.
problem Local statistical differences in ride-sourcing demand across a city.
method LC-ST-FCN framework combining 3D and 2D convolutions, locally connected layers.
result Significant improvements in demand forecasting compared to baselines.
Develops a deep learning approach for statistical arbitrage.
problem Temporal price differences between similar assets.
method Constructs arbitrage portfolios using latent asset pricing factors and a convolutional transformer for time series signals.
result High risk-adjusted returns and Sharpe ratios with optimal trading policy.
Study on Bayesian deep linear networks with multiple outputs and convolutional layers.
problem Characterize feature learning in finite-width Bayesian deep linear networks.
method Exact and analytical formulas for joint and posterior distributions, using large deviation theory.
result Quantitative description of feature learning in infinite-width regime.
This work proposes hyperbolic deep convolutional neural networks for better pattern recognition.
problem The limitations of Euclidean deep convolutional neural networks in capturing intricate patterns.
method Developed Hyperbolic DCNN based on Poincaré Disc, analyzing expansive convolution in non-Euclidean space.
result Hyperbolic convolutional architecture outperforms Euclidean ones in pattern recognition tasks.
The paper introduces a statistical distance matrix for better feature representation and clustering.
problem Lack of detailed distance representation between feature elements.
method Extended traditional statistical distance to a matrix form (statistical distance matrix) and applied hierarchical clustering.
result The statistical distance matrix with clustering (Information Mandala) provides clearer and geometrically arranged feature representations.
Graph convolutional networks fail to use eigenvectors beyond the first, unlike spectral embedding.
problem Understanding when graph convolutional networks fail compared to spectral embedding.
method Presented a simple generative model to illustrate failure.
result Graph convolutional networks fail to use eigenvectors beyond the first in certain graphs.
SCNN improves video object detection speed by 178%.
problem Limited throughput in existing CNNs for video object detection.
method Proposes SCNN, a statistical CNN that processes correlated distributions.
result Achieves 178% speedup over existing CNNs for video object detection.
New method shows fully-connected networks can learn convolutional structures from data.
problem How to learn convolutional structures from translation-invariant data.
method Data-driven emergence of convolutional structure in neural networks.
result Initially fully-connected networks can learn convolutional structures from their inputs.
The paper examines extreme value statistics of high-dimensional sample covariances, with applications in finance and image analysis.
problem Statistical validation of normal conditions in high-dimensional time series data.
method Generalizes the maximal deviation of sample autocovariances to high dimensions and applies Gumbel-type extreme value asymptotics.
result Gumbel-type extreme value asymptotics holds true for high-dimensional sample covariances.
We consider the problem of discrete-time signal denoising, focusing on a specific family of non-linear convolution-type estimators. Each such estimator is associated with a time-invariant filter which is obtained adaptively, by solving a certain convex optimization problem. Adaptive convolution-type estimators were dem…
New method uses CNNs to estimate graph means.
problem Estimating the mean of graph-valued data.
method Convolutional Neural Networks (CNNs) for graph morphology learning.
result CNNs reliably recover the sample Frechet mean.
In this work we detail the application of a fast convolution algorithm computing high dimensional integrals to the context of multiplicative noise stochastic processes. The algorithm provides a numerical solution to the problem of characterizing conditional probability density functions at arbitrary time, and we applie…
CNNs improve wind speed forecasts in the Netherlands.
problem Limited spatial patterns in current post-processing methods.
method Convolutional Neural Networks (CNNs) for spatial wind speed information.
result CNNs produce better probabilistic forecasts with higher Brier skill scores.
A new neural network model reduces features in high-dimensional sequential data.
problem Exponential growth in features of truncated signature transform in high-dimensional data.
method Proposes a neural network model inspired by Convolutional Neural Networks to address feature growth.
result Reduces the number of features efficiently in a data-dependent way.
New methods for geometric deep learning on manifolds.
problem Efficiently incorporating rotational effects and sampling on manifolds.
method Horizontal frame bundle flows and non-linear bridge sampling schemes.
result Efficient manifold convolution layers with weighted diffusion mean.
CNNs predict spatial fields from sparse data.
problem Predicting complete spatial fields from limited observations.
method Convolutional Neural Networks (CNNs) trained on a single partially observed field.
result CNNs can flexibly capture local spatial patterns without explicit covariance modeling.
Framework models female reproductive hormones with minimal invasive data.
problem Personalized modeling of female reproductive hormonal patterns.
method Combines multi-task Gaussian processes and dilated convolutional networks.
result Validated framework outperforms baseline methods in predictive performance.
DCCNNs reduce computational overhead and ambiguity in convolutional neural networks.
problem Reducing computational overhead and ambiguity in convolutional neural networks.
method Introducing a primal learning problem and constructing a dual convex training program, using Fenchel conjugates and Karush-Kuhn-Tucker conditions.
result Eliminates ambiguity and reduces computational overhead in constructing a large kernel matrix.
NN-Turb generates turbulent velocity statistics using neural networks.
problem Creating a 1D field with turbulent velocity statistics.
method Fully-convolutional neural network (NN-Turb) to generate the field.
result NN-Turb generates a 1D field that satisfies Kolmogorov's 2/3 and 4/5 laws, exhibiting intermittency.
GNNs generalize better on homophilic graphs than heterophilic ones.
problem Understanding the generalization error of GNNs on graph data.
method Analytical tools from statistical physics and random matrix theory.
result Risk is shaped by graph noise, feature noise, and training labels.
ConvResNets approximate Besov functions and classify on low-dimensional manifolds.
problem Lack of statistical theories for deep learning on high-dimensional data.
method Exploits low-dimensional geometric structures of real-world data sets using ConvResNets.
result ConvResNets can approximate Besov functions and learn classifiers with optimal excess risk.
CorGAN generates synthetic healthcare records while preserving privacy.
problem Generating realistic synthetic healthcare records while maintaining privacy.
method Combining Convolutional Generative Adversarial Networks and Convolutional Autoencoders to capture correlations between medical features.
result CorGAN generates synthetic data with performance similar to real data in various ML settings.
Generative adversarial networks with attention improve financial time series simulation.
problem Limited real financial data for training and evaluation of trading strategies.
method Two generative adversarial networks (GANs) using convolutional networks with attention and transformers.
result Attention-based GANs better reproduce stylized facts and smooth returns autocorrelation.
A generative Bayesian model is developed for deep (multi-layer) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up and top-down probabilistic learning. After learning the deep convolutional dictionary, testing is implemented via dec…
We establish linear regret bounds for convex smooth losses using Fenchel-Young losses.
problem Establishing linear regret bounds for convex smooth losses.
method Constructing a convex smooth surrogate loss using Fenchel-Young losses generated by the convolutional negentropy.
result We derive a smooth loss with a linear surrogate regret bound.
Researchers enhance EfficientNet models for practical efficiency on Graphcore IPU.
problem Improving practical efficiency of EfficientNet models on high-performance accelerators.
method Group convolutions, proxy-normalized activations, and reduced training resolution.
result Improves practical efficiency for both training and inference on Graphcore IPU.
PAN uses path integrals for graph convolution and pooling, improving GNN performance.
problem Designing efficient graph convolution and pooling for graph neural networks.
method Path integral based graph convolution and pooling using learnable weights for path lengths.
result PAN achieves state-of-the-art performance on various graph classification/regression tasks.
The study reveals flaws in pruning criteria and proposes a new assumption for better filter selection.
problem Flaws in existing pruning criteria for CNNs.
method Empirical experiments and Convolutional Weight Distribution Assumption.
result The Convolutional Weight Distribution Assumption improves filter selection in pruning.
ConvNP improves SP prediction with translation equivariance and coherent samples.
problem Predicting stationary stochastic processes with coherent samples.
method Convolutional Neural Processes (ConvNP) with a new maximum-likelihood objective.
result ConvNP outperforms standard NPs and demonstrates strong generalization on various tasks.
TransGCN combines GCNs with transformation assumptions for better link prediction in KGs.
problem Link prediction in knowledge graphs for understanding graph structure.
method Unified GCN framework with simultaneous learning of entity and relation embeddings, using transformation assumptions.
result TransGCN outperforms state-of-the-art models on FB15K-237 and WN18RR.
In this paper we present detailed simulation results on the wealth distribution model with quenched saving propensities. Unlike other wealth distribution models where the saving propensities are either zero or constant, this model is not found to be ergodic and self-averaging. The wealth distribution statistics with a …
Proposes a method to improve multi-output Gaussian process for transfer learning.
problem Negative transfer and domain inconsistency in multi-output Gaussian process.
method Regularized MGP with convolution process and domain adaptation.
result Outperforms state-of-the-art benchmarks in simulation and real-world studies.
This study compares deep learning and statistical models for stock price forecasting.
problem Accurate stock price prediction is challenging due to market volatility.
method Used deep learning (LSTM, RNN, CNN, FULL CNN) and statistical models (ARIMA, Moving Averages) on S&P 500 data.
result LSTM model showed the lowest Mean Absolute Error (MAE), indicating highest accuracy.
Deep neural network reconstructs traffic speeds from sparse vehicle data.
problem Reconstructing traffic speeds from limited probe vehicle data.
method Convolutional neural network architecture for spatio-temporal learning.
result The method can reconstruct traffic speeds with low probe vehicle penetration.
This research uses machine learning to approximate ideal and hotelling observer performance for binary signal detection.
problem Approximating the Ideal and Hotelling Observers for binary signal detection tasks.
method Supervised learning methods, including CNNs and SLNNs, are employed to approximate the IO and HO test statistics.
result The proposed supervised learning methods provide accurate approximations of the IO and HO test statistics.
Global covariance pooling improves deep CNNs' representation and generalization.
problem Capturing richer statistics of deep features for better representation and generalization.
method Integrates global covariance pooling into deep CNNs, addressing challenges with robust covariance estimation and geometry exploitation.
result Proposes MPN-COV Pooling and a Gaussian embedding network, achieving state-of-the-art performance.
PerCDL learns personalized dictionaries for physiological signals combining global and local structures.
problem Representing datasets with both global and local structures in human physiological signals.
method Personalized Convolutional Dictionary Learning (PerCDL) that combines a global and personalized local dictionary.
result PerCDL effectively learns interpretable representations for human locomotion data.
Transformer models perform slower than convolutional networks in learning hierarchical language structures.
problem Understanding how neural networks learn hierarchical language structures.
method Theoretical scaling laws and empirical validation of neural network performance.
result Convolutional networks outperform transformers in learning hierarchical language structures.
New deep network derived from rate reduction principles, explaining features and efficiency.
problem Understanding and optimizing deep learning architectures.
method Gradient ascent scheme for rate reduction leading to multi-layer deep network.
result Explicitly constructed multi-layer network with precise optimization and interpretation.
Convolutional neural networks show promise for flagging potential gravitational-wave signals.
problem Detecting gravitational waves from merging black holes in long data stretches.
method Convolutional neural networks applied to gravitational-wave detection.
result Convolutional neural networks can flag potential signals for follow-up analysis.
GraphSVR forecasts urban air pollution robustly across stations and seasons.
problem Nonlinear, nonstationary, spatiotemporally dependent urban air pollution forecasting challenges.
method Combines graph convolutional learning and support vector regression.
result GraphSVR improves predictive accuracy and maintains stable performance across seasons and outlier-prone episodes.
Statistical downscaling of global climate models (GCMs) allows researchers to study local climate change effects decades into the future. A wide range of statistical models have been applied to downscaling GCMs but recent advances in machine learning have not been explored. In this paper, we compare four fundamental st…
Study compares deep learning models for volatility prediction using multivariate data.
problem Predicting volatility using multivariate data.
method Evaluated multiple deep learning models including MLP, RNN, TCN, and Temporal Fusion Transformer.
result Temporal Fusion Transformer and TCN variants outperform classical models and shallow networks.