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.
Neural networks can separate non-separable data using feature maps.
Many applications generate data with an intrinsic network structure such as time series data, image data or social network data. The network Lasso (nLasso) has been proposed recently as a method for joint clustering and optimization of machine learning models for networked data. The nLasso extends the Lasso from sparse…
Method selects most useful network model for various tasks.
Multilayer switch networks are proposed as artificial generators of high-dimensional discrete data (e.g., binary vectors, categorical data, natural language, network log files, and discrete-valued time series). Unlike deconvolution networks which generate continuous-valued data and which consist of upsampling filters a…
Data symmetries in neural networks can generate conserved quantities.
There is often latent network structure in spatial and temporal data and the tools of network analysis can yield fascinating insights into such data. In this paper, we develop a nonparametric method for network reconstruction from spatiotemporal data sets using multivariate Hawkes processes. In contrast to prior work o…
Autoencoder neural network is implemented to estimate the missing data. Genetic algorithm is implemented for network optimization and estimating the missing data. Missing data is treated as Missing At Random mechanism by implementing maximum likelihood algorithm. The network performance is determined by calculating the…
A challenging problem in complex networks is the network reconstruction problem from data. This work deals with a class of networks denoted as conserved networks, in which a flow associated with every edge and the flows are conserved at all non-source and non-sink nodes. We propose a novel polynomial time algorithm to …
Paper improves Bayesian network learning from related data sets.
Bayesian network learns data invariances without augmentation.
Simplicial neural networks extend graph neural networks to handle higher-order interactions.
Currently, the world is witnessing a mounting avalanche of data due to the increasing number of mobile network subscribers, Internet websites, and online services. This trend is continuing to develop in a quick and diverse manner in the form of big data. Big data analytics can process large amounts of raw data and extr…
BSA reduces network data by interpreting feature subspaces.
Scattering networks maximize separation on low-dimensional data.
This paper presents a method for building patient-based networks that we call Precision disease networks, and its uses for predicting medical outcomes. Our methodology consists of building networks, one for each patient or case, that describes the dis-ease evolution of the patient (PDN) and store the networks as a set …
A hybrid neural network improves robustness in estimating vehicle parameters from noisy data.
Survey of data augmentation techniques for time series classification with neural networks.
Semiparametric Bayesian networks combine parametric and nonparametric models for flexible data analysis.
New method filters large networks from financial data to reveal key subnetworks.
Network structures in various backgrounds play important roles in social, technological, and biological systems. However, the observable network structures in real cases are often incomplete or unavailable due to measurement errors or private protection issues. Therefore, inferring the complete network structure is use…
We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data. Our approach provides a novel technique to classify big data sets using neural network models. We preprocess the data before training the neural network models. We first expand the data using wavel…
The paper presents a framework for estimating treatment effects using partial network data.
Generative Adversarial Networks create synthetic data for structural damage detection.
Modern data acquisition routinely produces massive amounts of network data. Though many methods and models have been proposed to analyze such data, the research of network data is largely disconnected with the classical theory of statistical learning and signal processing. In this paper, we present a new framework for …
FNNs detect EEG signals without position dependence.
New method reduces over-parametrization in neural networks, ensuring sparsity and finite network size.
A method for community detection in multilayer networks using data matrices.
Proposes a deep neural network for spatial data regression.
New neural network models for functional data.
New bound for neural nets on non-iid data.
SORSCNs improve nonstationary data modeling by self-organizing and adjusting network parameters.
Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads…
Improves stability in hyperbolic neural networks for complex data generation.
The network Lasso (nLasso) has been proposed recently as an efficient learning algorithm for massive networked data sets (big data over networks). It extends the well-known least absolute shrinkage and selection operator (Lasso) from learning sparse (generalized) linear models to network models. Efficient implementatio…
Proves generic existence of spectral networks for many cases.
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to…
Precision medicine has received attention both in and outside the clinic. We focus on the latter, by exploiting the relationship between individuals' social interactions and their mental health to develop a predictive model of one's likelihood to be depressed or anxious from rich dynamic social network data. To our kno…
Gradient descent biases towards stable rank networks for nearly-orthogonal data.
Study the effects of data parallelism and sparsity on neural network training.
We apply network Lasso to semi-supervised regression problems involving network structured data. This approach lends quite naturally to highly scalable learning algorithms in the form of message passing over an empirical graph which represents the network structure of the data. By using a simple non-parametric regressi…
Paper proposes an efficient algorithm for learning sparse Bayesian networks from discrete high-dimensional data.
Mobile big data contains vast statistical features in various dimensions, including spatial, temporal, and the underlying social domain. Understanding and exploiting the features of mobile data from a social network perspective will be extremely beneficial to wireless networks, from planning, operation, and maintenance…
Online Matrix Factorization (OMF) is a fundamental tool for dictionary learning problems, giving an approximate representation of complex data sets in terms of a reduced number of extracted features. Convergence guarantees for most of the OMF algorithms in the literature assume independence between data matrices, and t…
Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given t…
CupNet prunes neural nets for cup-shaped data.
Deep learning has become an area of interest in most scientific areas, including physical sciences. Modern networks apply real-valued transformations on the data. Particularly, convolutions in convolutional neural networks discard phase information entirely. Many deterministic signals, such as seismic data or electrica…
We propose networked exponential families to jointly leverage the information in the topology as well as the attributes (features) of networked data points. Networked exponential families are a flexible probabilistic model for heterogeneous datasets with intrinsic network structure. These models can be learnt efficient…
NON model improves tabular data classification accuracy.