Batch normalization makes deep residual networks train faster.
problem Training deep residual networks with large depths.
method Downscaling the residual branch by a normalizing factor early in training.
result Normalized residual blocks compute functions close to the identity function early in training.
Generalization bounds derived for neural ODEs and deep residual networks.
problem Understanding the generalization capability of neural ODEs and deep residual networks.
method Lipschitz-based argument and analogy with deep residual networks.
result A generalization bound involving the magnitude of weight matrix differences.
The skip-connections used in residual networks have become a standard architecture choice in deep learning due to the increased training stability and generalization performance with this architecture, although there has been limited theoretical understanding for this improvement. In this work, we analyze overparameter…
ResGCN detects anomalies in attributed networks by capturing sparsity and nonlinearity.
problem Detecting anomalous nodes in attributed networks.
method Attention-based deep residual modeling using Graph Convolutional Networks.
result ResGCN effectively detects anomalies in attributed networks.
Gradient descent converges globally in deep linear residual networks with ZAS initialization.
problem Optimizing deep linear residual networks for convergence.
method Zero-asymmetric (ZAS) initialization for gradient descent.
result Gradient descent converges to an ε-optimal point in O(L^3 log(1/ε)) iterations.
Study shows how deep residual networks can be analyzed as shallow network ensembles for optimization.
problem Understanding why deep neural networks can be trained to zero loss despite non-convex optimization landscapes.
method Mean-field analysis of deep residual networks, focusing on their continuum limit as a two-layer network.
result Derives the first global convergence result for multilayer neural networks in the mean-field regime.
Deep residual networks implicitly converge to neural ODEs.
problem Link between discrete and continuous deep learning models.
method Establishing implicit regularization for residual networks towards neural ODEs.
result Deep residual networks initialized as discretizations of neural ODEs converge to such ODEs during training.
Deep residual networks can approximate any continuous function using control theory.
problem Universal approximation capabilities of deep residual neural networks.
method Relating residual networks to control systems and using Lie algebraic techniques.
result Deep residual networks with adequately deep layers can approximate any continuous function on a compact set.
Adaptive weights improve physics-informed neural networks and deep operator networks.
problem Training physics-informed neural networks and deep operator networks can be challenging, leading to unsatisfactory accuracy and efficiency.
method Proposes a pointwise adaptive weighting method that balances the residual decay rate across different training points.
result Our proposed approach of balanced residual decay rates offers advantages including bounded weights, high prediction accuracy, fast convergence rate, low training uncertainty, low computational cost, and ease of hyperparameter tuning.
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …
Deep learning networks are approximated using dynamical systems theory.
problem Understanding the approximation capabilities of deep learning networks.
method Modeling deep residual networks as continuous-time dynamical systems and using approximation theories in Lp. result Established general sufficient conditions for universal approximation of deep residual networks.
SRFRN accelerates image super-resolution using shallow residual units.
problem High computational complexity and time in deep learning image super-resolution.
method SRFRN uses a bicubic interpolated low-resolution image and residual representative units (RFR) for faster and more efficient high-resolution image reconstruction.
result SRFRN achieves superior performance and faster execution time compared to existing methods.
Speeds up deep neural networks training by 10x using GPU concurrency.
problem Training deep residual neural networks efficiently.
method Layer-wise parallel training with GPU concurrency and Nonlinear Multigrid.
result 10.2x speedup over traditional techniques.
An emerging design principle in deep learning is that each layer of a deep artificial neural network should be able to easily express the identity transformation. This idea not only motivated various normalization techniques, such as \emph{batch normalization}, but was also key to the immense success of \emph{residual …
RDL-Net improves speech enhancement with fewer parameters and better performance.
problem Improving speech enhancement with fewer parameters and better performance.
method Proposes RDL-Net, a CNN combining residual and dense aggregations without over-allocating parameters.
result RDL-Net achieves higher speech enhancement performance with fewer parameters and lower computational requirements.
Theoretical limits of deep residual networks show consistent covariance structures.
problem Understanding the limits of deep residual networks.
method Analyzing the behavior of deep residual networks with skip connections as width and depth approach infinity.
result Theoretical analysis confirms that the covariance structure remains consistent regardless of the order of width and depth.
Residual connections significantly boost the performance of deep neural networks. However, there are few theoretical results that address the influence of residuals on the hypothesis complexity and the generalization ability of deep neural networks. This paper studies the influence of residual connections on the hypoth…
Deep learning enhances options hedging performance.
problem Improving delta hedging for options using neural networks.
method Learning residuals between hedging function and implied Black-Scholes delta using neural networks.
result Deep learning significantly improves hedging performance, often by more than 100%.
Graph neural networks suffer from oversmoothing, but adding residual connections helps.
problem Oversmoothing in deep graph neural networks where features become indistinguishable.
method Analyzed asymptotic oversmoothing rates with and without residual connections using the multiplicative ergodic theorem.
result Adding residual connections effectively mitigates or prevents oversmoothing.
New measure assesses deep neural networks' robustness to adversarial attacks.
problem Deep learning's fragility to adversarial attacks limits its adoption in mission-critical applications.
method Introduces residual error as a new performance measure for assessing adversarial robustness.
result Demonstrates effectiveness of residual error in assessing robustness of deep neural networks.
This paper explains why ResNets generalize better than FFNets using neural tangent kernels.
problem Understanding why deep ResNets generalize better than deep FFNets.
method Using neural tangent kernels to compare the learnability of functions induced by the kernels of ResNets and FFNets.
result The kernel of ResNets does not exhibit degeneracy as depth increases, unlike FFNets.
While training error of most deep neural networks degrades as the depth of the network increases, residual networks appear to be an exception. We show that the main reason for this is the Lyapunov stability of the gradient descent algorithm: for an arbitrarily chosen step size, the equilibria of the gradient descent ar…
To have a superior generalization, a deep learning neural network often involves a large size of training sample. With increase of hidden layers in order to increase learning ability, neural network has potential degradation in accuracy. Both could seriously limit applicability of deep learning in some domains particul…
Gradient descent converges to global minima for ResNets with linearly scaled width.
problem Understanding the convergence of deep residual networks with varying network width and dataset size.
method Analyzing the Jacobian of ResNets and applying gradient descent for quadratic loss.
result Gradient descent converges to global minima for ResNets with linearly scaled width and independent of depth.
Residual Network (ResNet) is the state-of-the-art architecture that realizes successful training of really deep neural network. It is also known that good weight initialization of neural network avoids problem of vanishing/exploding gradients. In this paper, simplified models of ResNets are analyzed. We argue that good…
Accelerated magnetic resonance (MR) scan acquisition with compressed sensing (CS) and parallel imaging is a powerful method to reduce MR imaging scan time. However, many reconstruction algorithms have high computational costs. To address this, we investigate deep residual learning networks to remove aliasing artifacts …
Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not poss…
We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In exp…
Stacking improves deep neural network training efficiency.
problem Improving the efficiency of training deep neural networks.
method Proposes stacking as a form of accelerated gradient descent.
result Proves stacking provides accelerated training for certain deep linear residual networks.
We present in this paper a model for forecasting short-term power loads based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers' understanding of the task by virtue of different neural network building blocks. Specifically, a modified deep residual network is formulated…
Review of neural network expressivity and architectures.
problem Understanding neural network expressivity across different architectures.
method Comprehensive overview of approximation results for various neural network types.
result Deep neural networks offer advantages over shallow ones for specific function classes.
Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized neural network with residual connections (ResNet). Our analysis relies on the p…
Enhances anomaly detection in high dimensions with pretrained networks.
problem Difficult to characterize anomaly in high-dimensional data.
method Residual adaptation to adjust pretrained networks for anomaly detection.
result Significantly outperforms existing methods on anomaly detection benchmarks.
ResNets promote smoother interpolations than MLPs, enhancing generalization.
problem Understanding the difference in smoothness between ResNets and MLPs.
method Neural Tangent Kernel (NTK) analysis during gradient descent training.
result ResNet's NTK results in smoother interpolations than MLPs.
Effective Gram matrix predicts deep network generalization.
problem Understanding and predicting deep network generalization.
method Derived a differential equation governing generalization gap, analyzed with effective Gram matrix.
result Effective Gram matrix accurately predicts test loss during training.
RFRBoost uses random features to boost deep residual neural networks, improving performance and computational efficiency.
problem Improving performance of deep residual neural networks (RFNNs) while preserving convex optimization benefits.
method Random Feature Representation Boosting (RFRBoost) using boosting theory and random features at each layer.
result RFRBoost significantly outperforms RFNNs and end-to-end trained MLP ResNets in small- to medium-scale tabular datasets.
Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with deeper and wider architectures. In this work, we interpret deep residual networks as ordinary differential equations (ODEs), which have long been s…
DAS-PINNs uses deep learning to solve complex PDEs more accurately.
problem Solving high-dimensional PDEs with high accuracy.
method Deep neural networks and generative models for adaptive sampling.
result DAS-PINNs significantly improves solution accuracy for low regularity and high-dimensional problems.
Deep linear ResNets converge globally with certain transformations.
problem Global convergence of training deep linear ResNets.
method Gradient descent and stochastic gradient descent for training L-hidden-layer linear ResNets. result GD and SGD can converge to global minimum for deep linear ResNets with specific transformations.
Generalized ResNet learns unknown dynamical systems using neural networks.
problem Learning unknown dynamical systems with deep neural networks.
method A generalized ResNet framework using discrepancy as model correction.
result Generalized ResNet produces more accurate predictions than standard ResNet.
Residual neural networks don't help overcome sampling complexity issues.
problem Learning invertible residual neural networks from samples is hard due to the curse of dimensionality.
method Investigated invertible residual neural networks and their sampling complexity.
result Invertible residual neural networks still suffer from the curse of dimensionality in sampling complexity.
This paper studies deep learning methodologies for portfolio optimization in the US equities market. We present a novel residual switching network that can automatically sense changes in market regimes and switch between momentum and reversal predictors accordingly. The residual switching network architecture combines …
Deep, wide ConvResNets can approximate functions and their smoothness.
problem Function approximation and smoothness in deep networks.
method Analyzing ConvResNets, proving their ability to approximate functions and their smoothness.
result Large ConvResNets can approximate functions and exhibit sufficient first-order smoothness.
Paper proposes continuous residual layers for graph neural networks.
problem Low-pass filtering effect in GCN-based models.
method Integrates Ordinary Differential Equations (ODE) to produce outputs of continuous residual layers.
result Continuous residual layers achieve better results than non-residual modules in multiple layers.
We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark. Moreover, we…
Subspace clustering aims to cluster unlabeled data that lies in a union of low-dimensional linear subspaces. Deep subspace clustering approaches based on auto-encoders have become very popular to solve subspace clustering problems. However, the training of current deep methods converges slowly, which is much less effic…
Proposes a cross-scale residual network for multiple image restoration tasks.
problem Image restoration tasks (super-resolution, denoising, deblocking) have strong correlations.
method Cross-scale residual network exploiting scale-related features and inter-task correlations.
result Outperforms state-of-the-art methods in multiple image restoration tasks.
Residual networks' depth is mathematically equivalent to expanding an implicit ensemble size.
problem Understanding why deep residual networks are effective.
method Formal analysis of residual networks as ensembles of shallow models.
result Increasing network depth is equivalent to expanding the size of an implicit ensemble, revealing a hierarchical structure.