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.

168,742 papers · 148 categories

Trend · papers per month

68136203271 · Jun 202019922001200920172026
48 results for wide DNNs

This paper explains robust overfitting in wide DNNs using adversarial training and NTK theory.

problem Robust overfitting in adversarially trained wide DNNs.
method Theoretical analysis using neural tangent kernel (NTK) theory and adversarial training dynamics.
result Adversarial training can lead to robust overfitting in wide DNNs, which can be mitigated by the proposed Adv-NTK method.

Improved DNN calibration without sacrificing accuracy.

problem Poor calibration of over-parametrized DNNs in safety-critical applications.
method Decoupling feature extraction and classification layers, and applying Gaussian priors.
result Significant improvement in model calibration with minimal training cost.

Embedding principle explains loss landscape of deep neural networks.

problem Understanding the structure of loss landscapes in deep neural networks.
method Proposed an embedding principle that critical points of narrower DNNs can be embedded to critical points of wider DNNs.
result Wide DNNs are often attracted by highly-degenerate critical points embedded from narrower DNNs.

Sparse DNNs face scalability issues; MIT/IEEE/Amazon challenge analyzes best solutions.

problem Scalability issues in Sparse Deep Neural Networks (DNNs).
method Mathematically defined DNN inference computation, community submissions from various fields.
result Sparse DNN execution time, TmDNNT_{ m DNN}, is strongly dependent on the number of operations, NmopN_{ m op}.

The wide adoption of DNNs has given birth to unrelenting computing requirements, forcing datacenter operators to adopt domain-specific accelerators to train them. These accelerators typically employ densely packed full precision floating-point arithmetic to maximize performance per area. Ongoing research efforts seek t…

2018-04-04abs ↗pdf ↗

Sublinearly structured DNNs achieve feature learning consistency for compositional functions.

problem Achieving feature-learning and prediction consistency in deep neural networks.
method Sublinearly structured DNNs
result Sublinearly structured DNNs match or surpass wide DNNs in prediction.

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.

Deep Neural Networks (DNNs) are universal function approximators providing state-of- the-art solutions on wide range of applications. Common perceptual tasks such as speech recognition, image classification, and object tracking are now commonly tackled via DNNs. Some fundamental problems remain: (1) the lack of a mathe…

2017-10-25abs ↗pdf ↗

The paper examines when NTK theory applies to real finite-width neural networks.

problem Understanding when NTK theory accurately predicts the behavior of finite-width neural networks.
method Empirical study of fully-connected ReLU and sigmoid DNNs with various hyperparameters and depths.
result NTK theory does not always apply to sufficiently deep networks with exploding gradients, and the kernel changes significantly during training.

Paper improves robustness and sparsity in adversarially trained DNNs.

problem Developing efficient compression algorithms for robustly trained DNNs.
method Pruning weights using relaxed augmented Lagrangian algorithms for both structured and unstructured levels, leveraging Feynman-Kac formalism.
result At least doubles channel sparsity of adversarially trained ResNet20 for CIFAR10 classification.

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.

New method improves interpretability of fMRI decoding models.

problem Uninterpretable deep neural networks in fMRI decoding.
method Adversarial training to make DNNs robust to noise and improved saliency map methods.
result Saliency maps from adversarial-trained DNNs are more interpretable than those from other methods.

CodNN uses error-correcting codes to make neural networks more resilient to noise.

problem Neural networks are sensitive to noise, especially in critical applications.
method Construct robust neural networks by coding data or internal layers with error-correcting codes.
result Parity codes can guarantee robustness for a wide range of neural networks, including binarized networks.

NetFuse merges different DNN models with varying weights for faster inference.

problem Inference speed of DNN models with different weights cannot be improved using existing techniques.
method NetFuse merges models with the same architecture but different weights and inputs, replacing operations with more general ones.
result NetFuse can speed up DNN inference time up to 3.6x on a NVIDIA V100 GPU.

The paper develops adaptive deep learning methods for nonlinear time series models.

problem Estimating mean functions of non-stationary and nonlinear time series models.
method Develops non-penalized and sparse-penalized DNN estimators for general non-stationary time series, derives minimax lower bounds, and shows the sparse-penalized DNN estimator is adaptive and optimal.
result Sparse-penalized DNN estimator achieves minimax optimal rates for many nonlinear AR models.

Winograd convolution is widely used in deep neural networks (DNNs). Existing work for DNNs considers only the subset Winograd algorithms that are equivalent to Toom-Cook convolution. We investigate a wider range of Winograd algorithms for DNNs and show that these additional algorithms can significantly improve floating…

2019-05-13abs ↗pdf ↗

Study compares memorization of SimCLR to supervised and random labels training.

problem Understanding memorization in contrastive learning.
method Investigated SimCLR's memorization properties compared to supervised and random labels training.
result SimCLR's memorization is similar to random labels training in terms of training object complexity distribution.

Study uses deep neural networks for causal inference tasks, especially in high-dimensional settings.

problem Challenges in direct estimation for complex causal inference tasks.
method Sequential multi-stage learning with doubly robust deep neural networks.
result Theoretical guarantees for DNNs' effectiveness in high-dimensional causal inference.

Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to the input, which undermines their true practicality. Recent works have increased the robustness of DNNs by fitting networks using adversarially…

2018-11-19abs ↗pdf ↗

The MIT/IEEE/Amazon GraphChallenge.org encourages community approaches to developing new solutions for analyzing graphs and sparse data. Sparse AI analytics present unique scalability difficulties. The proposed Sparse Deep Neural Network (DNN) Challenge draws upon prior challenges from machine learning, high performanc…

2019-09-02abs ↗pdf ↗

This paper connects deep neural networks to game theory, revealing their congestion game properties.

problem Understanding the behavior of deep neural networks using game theory.
method Analyzing deep neural networks as congestion games and applying game theory results.
result Deep neural networks exhibit congestion game properties, linking them to game theory.

This paper investigates the impact of normalization on deep neural networks for click-through rate prediction.

problem The effect of normalization on deep neural network models for CTR estimation.
method Systematic study of various normalization approaches applied to feature embedding and MLP part of DNN models.
result Correct normalization significantly enhances model performance, as demonstrated by extensive experiments on real-world datasets.

Paper develops deep neural networks for wireless tasks with reduced complexity.

problem Reducing training complexity for deep neural networks in wireless systems.
method Develops permutation invariant DNNs (PINNs) leveraging wireless task properties.
result Demonstrates dramatic reduction in training complexity for PINNs.

Paper proposes a method to estimate variance reduction in DNN training using importance sampling.

problem Challenges in assessing variance reduction during DNN training using importance sampling.
method Proposes a method for estimating variance reduction using minibatches sampled under importance sampling.
result Demonstrates consistent reduction in variance, improved training efficiency, and enhanced model accuracy.

The recent popularity of deep neural networks (DNNs) has generated a lot of research interest in performing DNN-related computation efficiently. However, the primary focus is usually very narrow and limited to (i) inference -- i.e. how to efficiently execute already trained models and (ii) image classification networks…

2018-03-16abs ↗pdf ↗

New sparsity attacks degrade DNN efficiency, raising concerns for resource-constrained systems.

problem Vulnerabilities in DNNs through energy and latency attacks.
method Proposed sparsity attacks that modify DNN inputs to reduce activation sparsity, increasing execution time and energy consumption.
result Adversarial sparsity attacks can degrade DNN efficiency by up to 1.82x in image recognition DNNs.

This paper proposes CSADA to make DNNs cost-sensitive.

problem Over-parameterization challenges cost-sensitive classification in DNNs.
method CSADA framework using adversarial data augmentation.
result CSADA effectively minimizes overall cost and reduces critical errors.

DP-Net uses dynamic programming for efficient deep neural network compression.

problem Efficiently compressing deep neural networks while maintaining accuracy.
method Dynamic Programming for optimal weight quantization and clustering-friendly training.
result Achieves up to 77X compression ratio on Wide ResNet with minimal accuracy loss.

Deep P-Spline automates DNN structure selection for complex regression problems.

problem Challenges in selecting optimal network structures for DNNs.
method Linking neuron selection to knot placement in basis expansion techniques, introducing a difference penalty for automated knot selection.
result Deep P-Spline extends model class and forms a latent variable modeling framework with theoretical guarantees.

Batch normalization shifts models to rely more on non-robust features.

problem Understanding the impact of batch normalization on deep neural networks.
method Empirical analysis and a framework for disentangling robustness and usefulness.
result Batch normalization increases reliance on non-robust features, decreasing adversarial robustness.

Analyzes DNNs trained with noisy gradients, finding FWCs negligible for large n.

problem Analyzing DNNs trained with noisy gradients.
method Introduced analytical framework to analyze non-Gaussian stochastic process.
result FWCs negligible for large n, improving CNN performance.