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.

168,695 papers · 148 categories

Trend · papers per month

3066129171,223 · Jun 202019922001200920172026
48 results for wide data

The paper analyzes knowledge distillation in wide neural networks, providing theoretical insights and practical implications.

problem Lack of theoretical understanding of knowledge distillation in wide neural networks.
method Theoretical analysis of knowledge distillation in a linearized model of a wide neural network, introducing a metric of task training difficulty.
result For a perfect teacher, a high ratio of teacher's soft labels can be beneficial. For imperfect teacher, hard labels can correct wrong predictions.

Wide residual networks generalize well with uniform convergence to RNTK as width increases.

problem Understanding the generalization ability of wide residual networks.
method Uniform convergence of residual network kernel to residual neural tangent kernel (RNTK).
result Generalization error converges to kernel regression error with respect to RNTK.

New learning rules for wide neural networks without backpropagation.

problem Training wide neural networks efficiently and without backpropagation.
method Input-weight alignment driven by gradient descent in the NTK regime.
result Biologically-motivated learning rules equivalent to backpropagation in wide networks.

Wide neural networks on R generalize well with early stopping.

problem Understanding generalization in wide neural networks.
method Analysis of spectral properties of NTK and NNK, convergence of NNK to NTK, minimax rates, and early stopping strategy.
result Wide neural networks trained with early stopping achieve the minimax rate and generalize well.

Wide BNNs with odd activations fail to approximate data under mean-field inference.

problem Theoretical limitations of mean-field variational inference in wide, deep Bayesian neural networks.
method Analysis of mean-field variational inference in fully-connected BNNs with odd activation functions and Gaussian likelihood.
result The optimal mean-field variational posterior predictive distribution converges to the prior predictive distribution as network width increases.

Independent Component Analysis (ICA) is a technique for unsupervised exploration of multi-channel data widely used in observational sciences. In its classical form, ICA relies on modeling the data as a linear mixture of non-Gaussian independent sources. The problem can be seen as a likelihood maximization problem. We i…

2017-11-29abs ↗pdf ↗

Wide and Deep GNN learns from distributed graphs and retrain online.

problem Decentralized graph support changes over time, causing mismatch between training and testing graphs.
method Wide and Deep GNN architecture with distributed online learning.
result Convergence guarantees for online retraining of the wide part of the GNN.

Feature selection from wide datasets leads to misleading results.

problem Feature selection in wide datasets with few samples can lead to misleading results.
method Derived sample size requirement for declaring features different, used real datasets to illustrate issues.
result Feature selection from very wide datasets may lead to misleading results.

Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms. The distributional uncertainty size is often shown to correspond to the regularization parameter. The type of regularization (e.g. the norm used to regularize)…

2017-05-19abs ↗pdf ↗

Gradient descent is a simple and widely used optimization method for machine learning. For homogeneous linear classifiers applied to separable data, gradient descent has been shown to converge to the maximal margin (or equivalently, the minimal norm) solution for various smooth loss functions. The previous theory does …

2019-07-26abs ↗pdf ↗

Wide neural networks' last hidden layers split into groups of redundant neurons.

problem Understanding why wide neural networks generalize well despite overfitting.
method Analyzed the last hidden layer representations of various convolutional neural networks.
result Wide hidden layers split into groups of redundant neurons, which help generalize.

Wide Bayesian neural networks have a simpler weight posterior, leading to faster MCMC sampling.

problem Sampling from the posterior of wide Bayesian neural networks is challenging.
method Introducing repriorisation, a data-dependent reparameterisation that simplifies the posterior distribution.
result The repriorisation map accelerates MCMC sampling, achieving up to 50x higher effective sample size.

ParKCa combines multiple causal inference methods to infer new causes from known and unknown factors.

problem Causal inference from observational data when randomized experiments are not feasible.
method ParKCa uses a stacking approach to combine results from multiple causal inference methods.
result ParKCa infers more causes than existing methods in real-world and simulated datasets.

With the wealth of high-throughput sequencing data generated by recent large-scale consortia, predictive gene expression modelling has become an important tool for integrative analysis of transcriptomic and epigenetic data. However, sequencing data-sets are characteristically large, and previously modelling frameworks …

2015-07-21abs ↗pdf ↗

Wide neural networks converge to Gaussian processes, improving generalization.

problem Understanding the generalization of wide neural networks, especially deep equilibrium models.
method Investigation of deep equilibrium models (DEQs) with infinite-depth layers, focusing on their convergence to Gaussian processes as width and depth approach infinity.
result Wide DEQs converge to Gaussian processes, maintaining generalization performance.

We study online linear regression problems in a distributed setting, where the data is spread over a network. In each round, each network node proposes a linear predictor, with the objective of fitting the \emph{network-wide} data. It then updates its predictor for the next round according to the received local feedbac…

2019-02-13abs ↗pdf ↗

Study on connectivity of Morse boundaries of Coxeter groups.

problem Connectivity of Morse boundaries of Coxeter groups.
method Defined conditions on defining graphs (wide-avoidant, wide-spherical-avoidant) and characterized Morse boundaries based on these conditions.
result Characterization of Morse boundary connectivity for different classes of Coxeter groups.

This study uses neural networks to solve interpolation problems with sparse, infinitely wide layers.

problem Exact data interpolation using sparse, infinitely wide neural networks.
method Atomic norm framework to derive convex hulls and equivalent convex formulations.
result Simple characterizations of convex hulls for different constraints on network weights and biases.

Wide networks learn from adversarial perturbations effectively.

problem Understanding why adversarial examples deceive classifiers and transfer between models.
method Assumed wide two-layer networks, proved with theoretical analysis.
result Adversarial perturbations contain class-specific features for networks to generalize.

Assessing world-wide financial integration constitutes a recurrent challenge in macroeconometrics, often addressed by visual inspections searching for data patterns. Econophysics literature enables us to build complementary, data-driven measures of financial integration using graphs. The present contribution investigat…

2019-05-28abs ↗pdf ↗

Wide neural networks with weight decay exhibit neural collapse.

problem Proving neural collapse in wide neural networks trained with weight decay.
method Generic guarantees on neural collapse for wide networks with weight decay, proving low training error and balancedness, and bounded conditioning.
result First proof of neural collapse in end-to-end training of wide neural networks with weight decay.

The paper reviews and improves concentration inequalities for statistical inference.

problem Analyzing statistical inference in various settings with high-dimensional data.
method Review and improvement of concentration inequalities for different types of random variables and statistical measures.
result Fresh new results and improved bounds with sharper constants.

Improved traffic forecasting model handles missing data.

problem Short-term traffic forecasting with missing values.
method Proposed SBU-LSTM architecture with bidirectional and unidirectional LSTM.
result Superior performance in accuracy and robustness for network-wide traffic prediction.

A new CA-GAN architecture improves minority class data generation in health datasets.

problem Algorithmic bias due to health data poverty and underrepresentation of minority groups.
method Proposes CA-GAN architecture to address shortcomings of resampling and GAN-based approaches.
result CA-GAN outperforms SMOTE and WGAN-GP* in generating authentic minority class data and maintaining original distribution.

Recent theoretical work has identified random projection as a promising dimensionality reduction technique for learning mixtures of Gausians. Here we summarize these results and illustrate them by a wide variety of experiments on synthetic and real data.

2013-01-16abs ↗pdf ↗

We prove the precise scaling, at finite depth and width, for the mean and variance of the neural tangent kernel (NTK) in a randomly initialized ReLU network. The standard deviation is exponential in the ratio of network depth to width. Thus, even in the limit of infinite overparameterization, the NTK is not determinist…

2019-09-13abs ↗pdf ↗

Sparse coding--that is, modelling data vectors as sparse linear combinations of basis elements--is widely used in machine learning, neuroscience, signal processing, and statistics. This paper focuses on the large-scale matrix factorization problem that consists of learning the basis set, adapting it to specific data. V…

2009-08-01abs ↗pdf ↗

Recent research shows that the following two models are equivalent: (a) infinitely wide neural networks (NNs) trained under l2 loss by gradient descent with infinitesimally small learning rate (b) kernel regression with respect to so-called Neural Tangent Kernels (NTKs) (Jacot et al., 2018). An efficient algorithm to c…

2019-10-03abs ↗pdf ↗