Write in a clean editor, then format for SIAM Journal on Mathematics of Data Science in one click — DocuGuru applies the official SIAM template with numbered references and exports a submission-ready PDF plus the editable LaTeX source. Free to start.
SIAM Journal on Mathematics of Data Science is a peer-reviewed journal published by SIAM, covering Sparse and Compressive Sensing Techniques, Stochastic Gradient Optimization Techniques, Neural Networks and Applications. Over its lifetime it has published 381 papers, which have received 3,584 citations.
| Publisher | SIAM |
|---|---|
| Reference style | Numbered (SIAM) Numbered — [1], [2] in the text [1] A. Smith, B. Jones, and C. Lee, A representative article title, SIAM Journal on Mathematics of Data Science 12 (2023) 45–58.
Formats any DOI in the closest standard style — SIAM Journal on Mathematics of Data Science has no published style definition, so this is an approximation. No sign-up. |
| Publishes research in | Sparse and Compressive Sensing Techniques Stochastic Gradient Optimization Techniques Neural Networks and Applications Statistical Methods and Inference Model Reduction and Neural Networks |
| ISSN | 2577-0187 |
| Citation impact (2-yr) | 1.79 |
| h-index | 28 |
| i10-index | 96 |
| Open access | Yes |
| Top institutions publishing here | Centre National de la Recherche Scientifique |
| Journal website | epubs.siam.org |
| You get | A submission-ready PDF and the editable LaTeX source — ready to submit. |
Citations each year’s papers have accumulated so far — the most recent years are still building up.
Matrices of (approximate) low rank are pervasive in data science, appearing in movie preferences, text documents, survey data, medical records, and genomics. While there is a vast literature on how to exploit low rank structure in these datasets, there is less attention paid to explaining why the low rank structure appears in the first place.…
The “double descent” risk curve was proposed to qualitatively describe the out-of-sample prediction accuracy of variably parameterized machine learning models. This article provides a precise mathematical analysis for the shape of this curve in two simple data models with the least squares/least norm predictor. Specifically, it is shown that the risk peaks when the number…
Related DatabasesWeb of Science You must be logged in with an active subscription to view this.Article DataHistorySubmitted: 17 January 2020Accepted: 11 January 2021Published online: 06 May 2021Keywordsneural networks, deep learning, function approximation, compressed sensing, numerical analysisAMS Subject Headings41A25, 41A46, 42C05, 65D05, 65D15, 65Y20, 94A20Publication DataISSN (online): 2577-0187Publisher: Society for Industrial and Applied MathematicsCODEN: sjmdaq
We prove a theorem concerning the approximation of multivariate functions by deep ReLU networks. We present new error estimates for which the curse of dimensionality is lessened by establishing a connection with sparse grids.
Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network.…
