arXiv research

Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more…

Wide deep neural networks are easy to optimize without constraints.

GCNIII combines Wide & Deep for better node classification.

Stable processes emerge as limits of deep neural networks with symmetric stable distributions.

Study of deep Stable neural networks with various activation functions.

Latent factor models have been used widely in collaborative filtering based recommender systems. In recent years, deep learning has been successful in solving a wide variety of machine learning problems. Motivated by the success of deep learning, we propose a deeper version of latent factor model. Experiments on benchm…

While classic studies proved that wide networks allow universal approximation, recent research and successes of deep learning demonstrate the power of deep networks. Based on a symmetric consideration, we investigate if the design of artificial neural networks should have a directional preference, and what the mechanis…

Deep networks with a wide layer ensure sublevel set connectivity.

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

Understanding the loss surface of neural networks is essential for the design of models with predictable performance and their success in applications. Experimental results suggest that sufficiently deep and wide neural networks are not negatively impacted by suboptimal local minima. Despite recent progress, the reason…

Wide deep neural networks with Gaussian weights approximate Gaussian processes closely.

Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connected, feedforward networks with more than one hidden layer and Gaussian processes with a recursive ker…

Bayesian inference for wide neural networks using Edgeworth expansion.

The paper examines how deep linear neural networks behave as they become infinitely wide.

We consider deep linear networks with arbitrary convex differentiable loss. We provide a short and elementary proof of the fact that all local minima are global minima if the hidden layers are either 1) at least as wide as the input layer, or 2) at least as wide as the output layer. This result is the strongest possibl…

Proposes efficient training method for deep thin networks.

We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has more neurons than the number of training samples. This condition holds e.g. for the…

Gradient descent proves global convergence for deep networks with a single wide layer.

Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and e…

Memory split advantage: thinner networks outperform a single wide network.

Recent works have shown that gradient descent can find a global minimum for over-parameterized neural networks where the widths of all the hidden layers scale polynomially with $N$ ($N$ being the number of training samples). In this paper, we prove that, for deep networks, a single layer of width $N$ following the inpu…

This Perspective provides examples of current and future applications of deep learning in pharmacogenomics, including: (1) identification of novel regulatory variants located in noncoding domains and their function as applied to pharmacoepigenomics; (2) patient stratification from medical records; and (3) prediction of…

Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose Neural Episodic Control: a deep reinforcement learning agent that is able to rap…

Study on infinitely-wide CNNs and their adaptability to function spatial scales.

Wide neural networks converge to Gaussian processes, improving generalization.

We prove that for an $L$-layer fully-connected linear neural network, if the width of every hidden layer is $\tildeΩ(L \cdot r \cdot d_{\mathrm{out}} \cdot κ^3 )$, where $r$ and $κ$ are the rank and the condition number of the input data, and $d_{\mathrm{out}}$ is the output dimension, then gradient descent with Gaussi…

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

This paper analyzes deep Stable neural networks, showing convergence rates under different growth settings.

WideBNet learns inverse scattering from wide-band data efficiently and stably.

Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods have a strong bias towards low- or high-order interactions, or rely on expertise feature engineering. In this paper, we show that it is possible to derive an …

Deep learning algorithms have achieved excellent performance lately in a wide range of fields (e.g., computer version). However, a severe challenge faced by deep learning is the high dependency on hyper-parameters. The algorithm results may fluctuate dramatically under the different configuration of hyper-parameters. A…

Paper proposes knockoff-based methods to simplify deep neural networks by controlling false discovery rates.

Article presents QR and LQ decomposition algorithms for various matrix sizes and ranks.

The paper proves neural networks' consistency and optimal convergence rates for various function classes.

Deep Gaussian Processes are reinterpreted as deep trigonometric networks for tractable inference.

Enhanced volatility model using LSTM and realized volatility.

Deep linear ResNets converge globally with certain transformations.

Attention mechanisms in deep learning become Gaussian process-like as the number of heads increases.

The paper uses deep learning to detect asset price bubbles in tech stocks.

Survey on deep models for graph generation.

Survey of deep learning models for scientific discovery.

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…

This paper provides a mathematical foundation for deep neural networks solving PDEs.

Deep neural networks (DNNs) have been widely used in the fields such as natural language processing, computer vision and image recognition. But several studies have been shown that deep neural networks can be easily fooled by artificial examples with some perturbations, which are widely known as adversarial examples. A…

Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine. Thus, deep RL opens up many new applications in domains such as healthcare, roboti…

Deep learning methods are useful for high-dimensional data and are becoming widely used in many areas of software engineering. Deep learners utilizes extensive computational power and can take a long time to train-- making it difficult to widely validate and repeat and improve their results. Further, they are not the b…

Study proves deep narrow RNNs can approximate any function, with minimum width independent of data length.

Nonconvex optimization problems such as the ones in training deep neural networks suffer from a phenomenon called saddle point proliferation. This means that there are a vast number of high error saddle points present in the loss function. Second order methods have been tremendously successful and widely adopted in the…