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.
Random convolutional networks can be fooled with adversarial examples.
New method uses CNNs to estimate graph means.
GCNs converge and remain stable on large random graphs, revealing geometric insights.
Rocket algorithm classifies time-series data efficiently using random projections and natural sparsity.
We propose a random convolutional neural network to generate a feature space in which we study image classification and retrieval performance. Put briefly we apply random convolutional blocks followed by global average pooling to generate a new feature, and we repeat this k times to produce a k-dimensional feature spac…
Convolution operations designed for graph-structured data usually utilize the graph Laplacian, which can be seen as message passing between the adjacent neighbors through a generic random walk. In this paper, we propose PAN, a new graph convolution framework that involves every path linking the message sender and recei…
This paper uses graph convolutional networks to improve the accuracy of neural architecture search.
Despite the superiority of convolutional neural networks demonstrated in time series modeling and forecasting, it has not been fully explored on the design of the neural network architecture and the tuning of the hyper-parameters. Inspired by the incremental construction strategy for building a random multilayer percep…
Deep neural networks achieve state-of-the-art performance for a range of classification and inference tasks. However, the use of stochastic gradient descent combined with the nonconvexity of the underlying optimization problems renders parameter learning susceptible to initialization. To address this issue, a variety o…
New multigrid approach reduces CNN parameters by focusing on structured convolutions.
Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets. Additionally, many existing methods focus on a single type of feature such as shape or frequency. …
CRITS improves time series classification with interpretable local explanations.
G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.
QCNNs avoid barren plateaus, making them trainable.
Adding node feature kernels improves GCN robustness to graph perturbations.
Untrained neural networks can recover natural images from few measurements.
GCNs distinguish graph models based on embeddings, but depth matters.
Randomized neural networks use fixed connections for efficiency.
Study on convergence of graph neural networks on random graphs.
Convolutional neural networks handle rotated image symmetries without dimensionality issues.
Observations depending on sums of random variables are common throughout many fields; however, no efficient solution is currently known for performing max-product inference on these sums of general discrete distributions (max-product inference can be used to obtain maximum a posteriori estimates). The limiting step to …
This paper introduces a generalization of Convolutional Neural Networks (CNNs) from low-dimensional grid data, such as images, to graph-structured data. We propose a novel spatial convolution utilizing a random walk to uncover the relations within the input, analogous to the way the standard convolution uses the spatia…
RR-GCN uses random transformations instead of learned weights for node embeddings.
Recently, reinforcement learning models have achieved great success, completing complex tasks such as mastering Go and other games with higher scores than human players. Many of these models collect considerable data on the tasks and improve accuracy by extracting visual and time-series features using convolutional neu…
GNNs generalize better on homophilic graphs than heterophilic ones.
Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. In this paper, we suggest to decompose convolutional filters in CNN as a truncated expansion with pre-fixed bases, namely the Decomposed Convolutional Filters network (DCFNet), where the expansion coefficient…
New methods learn from single graphs, improving transductive node classification.
Pixel-wise relevance method shows how CNNs classify faces, varying across datasets and tasks.
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by an arbitrary graph. Such structured sequences can represent series of frames in v…
Proposes BGCN-NRWS for semi-supervised node classification with reduced overfitting.
Random forest and deep neural network are two schools of effective classification methods in machine learning. While the random forest is robust irrespective of the data domain, the deep neural network has advantages in handling high dimensional data. In view that a differentiable neural decision forest can be added to…
Although the convolutional neural networks (CNNs) have become popular for various image processing and computer vision task recently, it remains a challenging problem to reduce the storage cost of the parameters for resource-limited platforms. In the previous studies, tensor decomposition (TD) has achieved promising co…
A new convolutional spectral kernel network learns hierarchical and local features.
Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how to leverage it more effectively, we focus on a theoretical explanation and develop a mathematical model of sparse signal recovery that is c…
WRS improves CNN hyperparameter optimization.
Convolutional architectures have recently been shown to be competitive on many sequence modelling tasks when compared to the de-facto standard of recurrent neural networks (RNNs), while providing computational and modeling advantages due to inherent parallelism. However, currently there remains a performance gap to mor…
This paper extends geometric study of neural networks to non-differentiable layers and random walks.
Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and therefore, end-to-end training is limited by GPU memory and data size. To overcome this issue, we introduce a netwo…
One of the fundamental problems in supervised classification and in machine learning in general, is the modelling of non-parametric invariances that exist in data. Most prior art has focused on enforcing priors in the form of invariances to parametric nuisance transformations that are expected to be present in data. Le…
Toxicity analysis and prediction are of paramount importance to human health and environmental protection. Existing computational methods are built from a wide variety of descriptors and regressors, which makes their performance analysis difficult. For example, deep neural network (DNN), a successful approach in many o…
Empirical study shows standard CNNs deviate from NTK predictions.
Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains a challenge. Here we de…
RAD enhances RL algorithms with data augmentations.
Study shows deterministic equivalent for neural network kernel convergence.
Random learning rate improves neural network training without extra cost.
LiPopt uses polynomial optimization to estimate neural network Lipschitz constants efficiently.
In a graph convolutional network, we assume that the graph is generated wrt some observation noise. During learning, we make small random perturbations of the graph and try to improve generalization. Based on quantum information geometry, can be characterized by the eigendecomposition of the graph Laplaci…
Recently, techniques for applying convolutional neural networks to graph-structured data have emerged. Graph convolutional neural networks (GCNNs) have been used to address node and graph classification and matrix completion. Although the performance has been impressive, the current implementations have limited capabil…