OOIR: Observatory of International Research

Papers

(The H4-Index of SIAM Journal on Mathematics of Data Science is 13. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2022-01-01 to 2026-01-01.)

Article	Citations
Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization	43
A Simple and Optimal Algorithm for Strict Circular Seriation	31
Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms	30
Spectral Barron Space for Deep Neural Network Approximation	28
On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions	25
A Note on the Regularity of Images Generated by Convolutional Neural Networks	23
Randomized Nyström Approximation of Non-negative Self-Adjoint Operators	23
New Equivalences between Interpolation and SVMs: Kernels and Structured Features	22
Poisson Reweighted Laplacian Uncertainty Sampling for Graph-Based Active Learning	18
Block Majorization Minimization with Extrapolation and Application to \({\beta }\)-NMF	17
Resolving the Mixing Time of the Langevin Algorithm to Its Stationary Distribution for Log-Concave Sampling	17
Learning Functions Varying along a Central Subspace	14
Efficient Algorithms for Regularized Nonnegative Scale-Invariant Low-Rank Approximation Models	14
Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning	13
Deep Block Proximal Linearized Minimization Algorithm for Nonconvex Inverse Problems	13
Online Machine Teaching under Learner Uncertainty: Gradient Descent Learners of a Quadratic Loss	13
Nonlinear Tomographic Reconstruction via Nonsmooth Optimization	13
Quantitative Approximation Results for Complex-Valued Neural Networks	13