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.
Study analyzes error in ReLU networks with local connections.
New heuristics for predicting links in multiplex networks.
DCGANs generate drainage networks quickly from samples.
The paper reveals surprising star-shaped connectivity in neural networks.
Law derived for neural networks with sparse connections.
This paper improves deep neural network approximation for fully connected networks, achieving optimal convergence rates.
The paper proves skip connections help neural networks avoid shallow local minima.
USN improves neural networks with uniform sparse connectivity.
Paper analyzes the free energy of CNNs with skip connections in Bayesian learning.
This work refines claims about neural network connectivity, showing that simultaneous linear connectivity is possible under certain conditions.
Geodesics connect model modes in neural network loss landscapes.
LOCUS separates brain network connectivity matrices efficiently.
We consider the problem of accelerating distributed optimization in multi-agent networks by sequentially adding edges. Specifically, we extend the distributed dual averaging (DDA) subgradient algorithm to evolving networks of growing connectivity and analyze the corresponding improvement in convergence rate. It is know…
Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods exist for pruning connections of a neural network after it was trained without conne…
We generalize the scale-free network model of Barabàsi and Albert [Science 286, 509 (1999)] by proposing a class of stochastic models for scale-free interdependent networks in which interdependent nodes are not randomly connected but rather are connected via preferential attachment (PA). Each network grows through 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…
Proposes using mode connectivity to improve adversarial robustness of neural networks.
Method estimates network connectivity and dimensionality from multiple networks.
Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another …
Nontrivial connectivity has allowed the training of very deep networks by addressing the problem of vanishing gradients and offering a more efficient method of reusing parameters. In this paper we make a comparison between residual networks, densely-connected networks and highway networks on an image classification tas…
A new kernel measures brain network similarities, improving disease classification.
Neural networks can learn optimal auction mechanisms and satisfy mode connectivity.
Sparse connectivity improves generalization in neural networks below the Edge of Stability.
PAC-Bayesian bounds show fully connected DNNs with Gaussian priors match minimax rates.
Model predicts loan default risk using dynamic multilayer graph neural networks.
New framework for dense weighted networks with community-specific patterns.
Previous work has questioned the conditions under which the decision regions of a neural network are connected and further showed the implications of the corresponding theory to the problem of adversarial manipulation of classifiers. It has been proven that for a class of activation functions including leaky ReLU, neur…
Due to the success of residual networks (resnets) and related architectures, shortcut connections have quickly become standard tools for building convolutional neural networks. The explanations in the literature for the apparent effectiveness of shortcuts are varied and often contradictory. We hypothesize that shortcut…
New methods connect low-loss points on neural network surfaces.
Interneurons improve learning in neural networks by accelerating convergence.
We explain that spectral networks are a unifying framework that incorporates both shear (Fock-Goncharov) and length-twist (Fenchel-Nielsen) coordinate systems on moduli spaces of flat SL(2,C) connections, in the following sense. Given a spectral network W on a punctured Riemann surface C, we explain the process of "abe…
Deep networks with a wide layer ensure sublevel set connectivity.
We exploit altered patterns in brain functional connectivity as features for automatic discriminative analysis of neuropsychiatric patients. Deep learning methods have been introduced to functional network classification only very recently for fMRI, and the proposed architectures essentially focused on a single type of…
Graph neural networks suffer from oversmoothing, but adding residual connections helps.
Proposes neuron alignment to optimize mode connectivity in neural networks.
This paper addresses the problem of inferring sparse causal networks modeled by multivariate auto-regressive (MAR) processes. Conditions are derived under which the Group Lasso (gLasso) procedure consistently estimates sparse network structure. The key condition involves a "false connection score." In particular, we sh…
The paper connects neural networks to Mahalanobis distance for interpretability.
This comment reexamines Simard et al.'s work in [D. Simard, L. Nadeau, H. Kroger, Phys. Lett. A 336 (2005) 8-15]. We found that Simard et al. calculated mistakenly the local connectivity lengths Dlocal of networks. The right results of Dlocal are presented and the supervised learning performance of feedforward neural n…
Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a c…
Development of stock networks is an important approach to explore the relationship between different stocks in the era of big-data. Although a number of methods have been designed to construct the stock correlation networks, it is still a challenge to balance the selection of prominent correlations and connectivity of …
The study shows removing fully connected output layers improves efficiency without sacrificing performance.
Networks are a fundamental model of complex systems throughout the sciences, and network datasets are typically analyzed through lower-order connectivity patterns described at the level of individual nodes and edges. However, higher-order connectivity patterns captured by small subgraphs, also called network motifs, de…
Pruning FCNs reveals sub-networks that match CNNs' performance.
Dynamics and function of neuronal networks are determined by their synaptic connectivity. Current experimental methods to analyze synaptic network structure on the cellular level, however, cover only small fractions of functional neuronal circuits, typically without a simultaneous record of neuronal spiking activity. H…
New methods train neural networks without changing weights, achieving similar or higher performance.
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), w…
Community detection is a fundamental task in social network analysis. In this paper, first we develop an endorsement filtered user connectivity network by utilizing Heider's structural balance theory and certain Twitter triad patterns. Next, we develop three Nonnegative Matrix Factorization frameworks to investigate th…