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

162324486648 · Jun 202019922001200920172026
48 results for deep normalization

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.

The paper proposes deep normalization to improve speaker recognition performance.

problem Non-Gaussian and non-homogeneous distributions of deep speaker vectors negatively impact speaker recognition.
method Proposes a deep normalization approach based on a novel discriminative normalization flow (DNF) model.
result DNF-based normalization delivers substantial performance gains and strong generalization capability.

Normalization layers improve the accuracy of Differentially Private training of deep neural networks.

problem Reduced accuracy in deep neural networks with Differentially Private training.
method Proposed a novel method for integrating batch normalization with Differentially Private Stochastic Gradient Descent (DPSGD) without additional privacy loss.
result Training deeper networks with better utility-privacy trade-off is possible.

Normalization layers control deep neural network capacity, improving stability and generalization.

problem Excessive capacity in deep neural networks leads to overfitting and poor generalization.
method Developed a theoretical framework to explain normalization's role in capacity control.
result Normalization layers reduce the Lipschitz constant exponentially, smoothing the loss landscape and enhancing generalization.

Proposes a new normalization method for deep neural networks in financial forecasting.

problem Deep neural networks are sensitive to input variable range and prone to numerical issues, especially with financial time-series.
method Bilinear input normalization method that handles high-frequency financial time-series without expert knowledge.
result Significant improvements in forecasting future stock price dynamics over other normalization techniques.

Batch normalization prevents rank collapse in deep networks, improving training stability.

problem Rank collapse in randomly initialized deep networks with increasing depth.
method Investigates spectral instabilities in random matrices and uses batch normalization to avoid rank collapse.
result Batch normalization prevents rank collapse in both linear and ReLU networks, improving training stability.

This paper analyzes how normalization layers improve neural network training.

problem Improving generalization performance and training speed of neural networks.
method Global convergence analysis of two-layer neural networks with ReLU activations and Weight Normalization.
result Introduction of normalization layers changes the optimization landscape, enabling faster convergence.

This paper presents a general framework for norm-based capacity control for Lp,qL_{p,q} weight normalized deep neural networks. We establish the upper bound on the Rademacher complexities of this family. With an Lp,qL_{p,q} normalization where qpq\le p^*, and 1/p+1/p=11/p+1/p^{*}=1, we discuss properties of a width-independent ca…

2018-10-03abs ↗pdf ↗

GAS-Norm improves deep learning time series forecasting in non-stationary settings.

problem Deep learning models struggle with non-stationary time series data.
method Combines GAS model for adaptive normalization with deep neural networks.
result Improves deep learning performance in 21 out of 25 settings.

EDAIN layer normalizes time series data for neural networks, improving model performance.

problem Irregularities in time series data degrade model performance in neural networks.
method EDAIN layer learns adaptive normalization parameters during end-to-end training.
result EDAIN layer outperforms conventional normalization methods and adaptive layers.

Enhances DNN robustness and accuracy with L2,L_{2,\infty} normalization.

problem Improving the robustness and accuracy of deep neural networks.
method Introducing L2,L_{2,\infty} normalization of weight matrices in DNNs with Relu activation.
result Lower bound for robustness measure in terms of L2,L_{2,\infty} norm and upper bound for Rademacher complexity.

This paper explains how batch normalization auto-tunes the regularization parameter based on data statistics.

problem Batch normalization accelerates deep learning training but the exact relationship to regularization is unclear.
method Theoretical analysis and empirical validation of batch normalization's role in auto-tuning the regularization parameter.
result Batch normalization auto-tunes the regularization parameter based on data statistics.

Lipschitz normalization boosts deep attention models, especially for graph neural networks.

problem Gradient explosion in deep graph attention networks leads to poor performance.
method Enforcing Lipschitz continuity by normalizing attention scores.
result Deep GAT models with LipschitzNorm achieve state-of-the-art results for tasks with long-range dependencies.

We improve neural network explainability by bypassing batch normalization.

problem Lack of transparency in neural networks.
method Layer-wise Relevance Propagation with a method to include normalization layers.
result Heatmaps are more accurate for convolutional layers with our method.

Adaptive feature normalization improves model robustness to extraneous variables.

problem Degrading model performance due to extraneous variables in deep learning.
method Adaptive feature normalization using instance normalization instead of batch normalization.
result Adaptive normalization leads to significant performance gains across different datasets and architectures.

Proposes a method to detect anomalies in multi-subgroup normal data.

problem Anomaly detection with limited labeled anomalies and multi-subgroup normal data.
method Learn multi-normal prototypes with deep embedding clustering and contrastive learning. Estimate the likelihood of unlabeled samples being normal during training.
result Superior performance compared to state-of-the-art methods on various datasets.

In this paper we introduce a novel method of gradient normalization and decay with respect to depth. Our method leverages the simple concept of normalizing all gradients in a deep neural network, and then decaying said gradients with respect to their depth in the network. Our proposed normalization and decay techniques…

2017-12-10abs ↗pdf ↗

Proposes group whitening to enhance deep learning models' performance.

problem Improving learning efficiency and representational capacity in deep learning models.
method Group Whitening (GW) combines whitening and group normalization to balance these aspects.
result Group Whitening consistently improves model performance across different architectures and benchmarks.

SAM optimizer benefits from normalization, stabilizing and guiding optimization.

problem Improving deep neural network performance with SAM optimizer.
method Theoretical and empirical study of normalization in SAM for convex and non-convex functions.
result Normalization helps SAM in stabilizing and guiding optimization along a continuum of minima.

Improves anomaly detection with contaminated unlabeled data.

problem Weakness in existing semi-supervised anomaly detection methods when unlabeled data contain anomalies.
method Integrates positive-unlabeled learning with deep anomaly detection models.
result Achieves better detection performance on various datasets.

Layer normalization with activations prevents Gram matrix rank collapse at initialization.

problem Rank collapse in Gram matrices at initialization slows training in deep networks.
method Proved that layer normalization, with activation layers, biases Gram matrix towards identity matrix at exponential rate.
result Layer normalization with activations biases Gram matrix towards identity matrix at exponential rate with depth at initialization.

New method trains deep ResNets without normalization, achieving state-of-the-art performance.

problem Training deep ResNets without normalization layers leads to instability and lower accuracy.
method Adaptive gradient clipping and Normalizer-Free ResNets design.
result Normalizer-Free ResNets achieve 86.5% top-1 accuracy on ImageNet, matching EfficientNet-B7.

Class Normalization improves zero-shot learning models.

problem Improving zero-shot learning models in a continual setting.
method Class Normalization (CN) technique to address irregular loss surfaces and improve training efficiency.
result CN significantly outperforms state-of-the-art models on 4 standard ZSL datasets.

Normalization methods are a central building block in the deep learning toolbox. They accelerate and stabilize training, while decreasing the dependence on manually tuned learning rate schedules. When learning from multi-modal distributions, the effectiveness of batch normalization (BN), arguably the most prominent nor…

2018-10-12abs ↗pdf ↗

NVAE improves VAE performance on large image datasets.

problem Improving variational autoencoder performance for large image datasets.
method Deep hierarchical VAE with depth-wise separable convolutions and batch normalization, residual parameterization of Normal distributions, and spectral regularization.
result NVAE achieves state-of-the-art results on MNIST, CIFAR-10, CelebA 64, and CelebA HQ datasets.

Normalization effects on deep neural networks impact output variance and test accuracy.

problem The impact of normalization on deep neural networks' statistical behavior and test accuracy.
method Asymptotic expansion analysis of neural network's output for different γiγ_i values.
result Equal γiγ_i values (one) provide the best statistical behavior and test accuracy.

Deep approaches to anomaly detection have recently shown promising results over shallow methods on large and complex datasets. Typically anomaly detection is treated as an unsupervised learning problem. In practice however, one may have---in addition to a large set of unlabeled samples---access to a small pool of label…

2019-06-06abs ↗pdf ↗

This research investigates if deep neural networks can be trained without batch normalization.

problem Training deep neural networks efficiently without batch normalization.
method Detailed study of batch normalization, comparison with other methods, and adaptation of training process.
result It is possible to train deep neural networks effectively without batch normalization.