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.
Convolutional networks outperform fully-connected ones in certain tasks.
This paper improves deep neural network approximation for fully connected networks, achieving optimal convergence rates.
The study shows removing fully connected output layers improves efficiency without sacrificing performance.
PAC-Bayesian bounds show fully connected DNNs with Gaussian priors match minimax rates.
Convolutional nets require fewer samples than fully-connected nets for image classification.
Generative Adversarial Networks (GANs) are a powerful class of generative models. Despite their successes, the most appropriate choice of a GAN network architecture is still not well understood. GAN models for image synthesis have adopted a deep convolutional network architecture, which eliminates or minimizes the use …
Artificial Neural Networks form the basis of very powerful learning methods. It has been observed that a naive application of fully connected neural networks to data with many irrelevant variables often leads to overfitting. In an attempt to circumvent this issue, a prior knowledge pertaining to what features are relev…
In this paper, we propose a novel multi-task learning method based on the deep convolutional network. The proposed deep network has four convolutional layers, three max-pooling layers, and two parallel fully connected layers. To adjust the deep network to multi-task learning problem, we propose to learn a low-rank deep…
We study alignment in linear neural networks and its relation to gradient descent.
This article demonstrates that convolutional operation can be converted to matrix multiplication, which has the same calculation way with fully connected layer. The article is helpful for the beginners of the neural network to understand how fully connected layer and the convolutional layer work in the backend. To be c…
USN improves neural networks with uniform sparse connectivity.
FC-GAGA forecasts traffic using a novel gating mechanism.
Pruning FCNs reveals sub-networks that match CNNs' performance.
Recurrent neural networks (RNNs) are omnipresent in sequence modeling tasks. Practical models usually consist of several layers of hundreds or thousands of neurons which are fully connected. This places a heavy computational and memory burden on hardware, restricting adoption in practical low-cost and low-power devices…
Transformers excel at sparse token selection, surpassing FCNs in both worst and average cases.
In this empirical paper, we investigate how learning agents can be arranged in more efficient communication topologies for improved learning. This is an important problem because a common technique to improve speed and robustness of learning in deep reinforcement learning and many other machine learning algorithms is t…
In this work, we leverage advances in sparse coding techniques to reduce the number of trainable parameters in a fully connected neural network. While most of the works in literature impose regularization, DropOut or DropConnect techniques to induce sparsity, our scheme considers feature importance as a criter…
We present a transductive deep learning-based formulation for the sparse representation-based classification (SRC) method. The proposed network consists of a convolutional autoencoder along with a fully-connected layer. The role of the autoencoder network is to learn robust deep features for classification. On the othe…
We consider the effects of the global financial crisis through a local Korean financial market around the 2008 crisis. We analyze 185 individual stock prices belonging to the KOSPI (Korea Composite Stock Price Index), cosidering three time periods: the time before, during, and after the crisis. The complex networks gen…
In this paper, we will describe a network architecture that demonstrates high performance on various sizes of datasets. To do this, we will perform an architecture search by dividing the fully connected layer into three levels in the existing network architecture. The first step is to learn existing CNN layer and exist…
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters. Reducing the number of parameters while preserving essentially the same predictive performance is critically important …
Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers. We adapt this approach to the convolutional setting.
Proves DCNNs with expansive convolution are strongly universally consistent.
Deep neural networks estimate regression functions on manifolds.
Multivariate techniques based on engineered features have found wide adoption in the identification of jets resulting from hadronic top decays at the Large Hadron Collider (LHC). Recent Deep Learning developments in this area include the treatment of the calorimeter activation as an image or supplying a list of jet con…
Recently popularized graph neural networks achieve the state-of-the-art accuracy on a number of standard benchmark datasets for graph-based semi-supervised learning, improving significantly over existing approaches. These architectures alternate between a propagation layer that aggregates the hidden states of the local…
New method shows fully-connected networks can learn convolutional structures from data.
In our previous work we have shown that resistive cross point devices, so called Resistive Processing Unit (RPU) devices, can provide significant power and speed benefits when training deep fully connected networks as well as convolutional neural networks. In this work, we further extend the RPU concept for training re…
Quantitative CLTs show neural network distributions converge to Gaussian as width increases.
Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposing low tensor rank structure on the weight matrices of fully connected layers. In recent years, tensor regression networks have been investigated from the perspective of their comp…
Deep neural networks are powerful learning models that achieve state-of-the-art performance on many computer vision, speech, and language processing tasks. In this paper, we study a fundamental question that arises when designing deep network architectures: Given a target network architecture can we design a smaller ne…
Stable processes emerge as limits of deep neural networks with symmetric stable distributions.
Study examines noise sensitivity of DNNs for binary classification.
The past few years have witnessed the fast development of different regularization methods for deep learning models such as fully-connected deep neural networks (DNNs) and Convolutional Neural Networks (CNNs). Most of previous methods mainly consider to drop features from input data and hidden layers, such as Dropout, …
Recent results in nonparametric regression show that deep learning, i.e., neural network estimates with many hidden layers, are able to circumvent the so-called curse of dimensionality in case that suitable restrictions on the structure of the regression function hold. One key feature of the neural networks used in the…
We propose Sparse Neural Network architectures that are based on random or structured bipartite graph topologies. Sparse architectures provide compression of the models learned and speed-ups of computations, they can also surpass their unstructured or fully connected counterparts. As we show, even more compact topologi…
The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact o…
Unified method for deriving ridgelet transforms for various neural network architectures.
We show that gradient descent on full-width linear convolutional networks of depth converges to a linear predictor related to the bridge penalty in the frequency domain. This is in contrast to linearly fully connected networks, where gradient descent converges to the hard margin linear support vector m…
A common technique to improve learning performance in deep reinforcement learning (DRL) and many other machine learning algorithms is to run multiple learning agents in parallel. A neglected component in the development of these algorithms has been how best to arrange the learning agents involved to improve distributed…
The paper sets information-theoretic lower bounds for neural networks' parameter recovery and excess risk.
Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e.g., computer Go. However, very little work has been done in deep RL to handle partially observable environments. We propose a new architec…
The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of inductive bias that constrains the functions learned through the optimization process to concentrate a…
This paper extends ResNet theory to infinitely deep networks, linking them to diffusion processes.
In this paper we study the generalization capabilities of fully-connected neural networks trained in the context of time series forecasting. Time series do not satisfy the typical assumption in statistical learning theory of the data being i.i.d. samples from some data-generating distribution. We use the input and weig…
There has been significant interest in the use of fully-connected graphical models and deep-structured graphical models for the purpose of structured inference. However, fully-connected and deep-structured graphical models have been largely explored independently, leaving the unification of these two concepts ripe for …
Unified theorem for deep and shallow joint-equivariant machines.
The paper calculates bounds on the local Lipschitz constants of neural network layers.