Data science is everywhere, but how does it actually work? SIAM’s newest journal, the SIAM Journal on Mathematics of Data Science (SIMODS), aims to understand the deep inner workings of machine learning, artificial intelligence, signal processing, network science, and much more, championing the key role of mathematics within the increasingly important domain of data science.
SIAM Journal on Mathematics of Data Science (SIMODS) publishes work that advances mathematical, statistical, and computational methods in the context of data and information sciences. We invite papers that present significant advances in this context, including applications to science, engineering, business, and medicine.
Editor-in-Chief Tamara G. Kolda says, “As we move forward, SIMODS will establish mathematics' importance in the fast-growing domain of data science and serve as a home for those that work at this crossroads of mathematics, statistics, computer science, network science, signal processing, and other fields...We aim to have articles that challenge traditional thinking next to ones that explain the successes (and failures) of existing methods…We anticipate that these papers will not only be useful to data sciences but also have ramifications for traditional areas of applied mathematics research as they incorporate methods that have advanced in the data science regime.”
Read the 10 most-downloaded SIMODS articles thus far:
- Why Are Big Data Matrices Approximately Low Rank? (Madeleine Udell and Alex Townsend)
- Sequential Sampling for Optimal Weighted Least Squares Approximations in Hierarchical Spaces (Benjamin Arras, Markus Bachmayr, and Albert Cohen)
- Gaussian Process Landmarking on Manifolds (Tingran Gao, Shahar Z. Kovalsky, and Ingrid Daubechies)
- Gaussian Process Landmarking for Three-Dimensional Geometric Morphometrics (Tingran Gao, Shahar Z. Kovalsky, Doug M. Boyer, and Ingrid Daubechies)
- Optimal Approximation with Sparsely Connected Deep Neural Networks (Helmut Bolcskei, Philipp Grohs, Gitta Kutyniok, and Phillipp Petersen)
- The Rankability of Data (Paul Anderson, Timothy Chartier, and Amy Langville)
- A Nonlinear Spectral Method for Core-Periphery Detection in Networks (Francesco Tudisco and Desmond J. Higham)
- Clustering with t-SNE, Provably (George C. Linderman and Stefan Steinerberger)
- Multivariate Spatiotemporal Hawkes Processes and Network Reconstruction (Baichuan Yuan, Hao Li, Andrea L. Bertozzi, P. Jeffrey Brantingham, and Mason A. Porter)
- New Error Bounds for Deep ReLU Networks Using Sparse Grids (Hadrien Montanelli and Qiang Du)
SIMODS began publishing articles electronically to Volume 1 in February 2019. Articles in Issue 1 and 2 are available for free through the end of 2020 here.