OOIR: Observatory of International Research

Papers

(The median citation count of SIAM Journal on Mathematics of Data Science is 2. 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 2022-05-01 to 2026-05-01.)

Article	Citations
Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization	45
Spectral Barron Space for Deep Neural Network Approximation	35
A Simple and Optimal Algorithm for Strict Circular Seriation	34
Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms	33
A Note on the Regularity of Images Generated by Convolutional Neural Networks	28
New Equivalences between Interpolation and SVMs: Kernels and Structured Features	22
Quantitative Approximation Results for Complex-Valued Neural Networks	20
Learning Functions Varying along a Central Subspace	19
Deep Block Proximal Linearized Minimization Algorithm for Nonconvex Inverse Problems	17
Block Majorization Minimization with Extrapolation and Application to ${\beta }$-NMF	17
Randomized Nyström Approximation of Non-negative Self-Adjoint Operators	14
Poisson Reweighted Laplacian Uncertainty Sampling for Graph-Based Active Learning	14
On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions	14
Efficient Algorithms for Regularized Nonnegative Scale-Invariant Low-Rank Approximation Models	14
Resolving the Mixing Time of the Langevin Algorithm to Its Stationary Distribution for Log-Concave Sampling	13
Nonlinear Tomographic Reconstruction via Nonsmooth Optimization	12
Online Machine Teaching under Learner Uncertainty: Gradient Descent Learners of a Quadratic Loss	12
Nonbacktracking Spectral Clustering of Nonuniform Hypergraphs	11
Persistent Laplacians: Properties, Algorithms and Implications	11
Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning	11
Safe Rules for the Identification of Zeros in the Solutions of the SLOPE Problem	11
Scalable Tensor Methods for Nonuniform Hypergraphs	10
Convergence of a Piggyback-Style Method for the Differentiation of Solutions of Standard Saddle-Point Problems	10
Stochastic Variance-Reduced Majorization-Minimization Algorithms	9
A Notion of Uniqueness for the Adversarial Bayes Classifier	9

Nonlinear Meta-learning Can Guarantee Faster Rates	9
Asymptotics of the Sketched Pseudoinverse	9
Learning Memory Kernels in Generalized Langevin Equations	9
CA-PCA: Manifold Dimension Estimation, Adapted for Curvature	9
Covariance Alignment: From Maximum Likelihood Estimation to Gromov–Wasserstein	9
Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities	9
Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis	8
Inverse Evolution Layers: Physics-Informed Regularizers for Image Segmentation	8
Bi-Invariant Dissimilarity Measures for Sample Distributions in Lie Groups	8
A Variational Formulation of Accelerated Optimization on Riemannian Manifolds	8
Group-Invariant Tensor Train Networks for Supervised Learning	8
The GenCol Algorithm for High-Dimensional Optimal Transport: General Formulation and Application to Barycenters and Wasserstein Splines	8
The Sample Complexity of Sparse Multireference Alignment and Single-Particle Cryo-Electron Microscopy	8
On Neural Network Approximation of Ideal Adversarial Attack and Convergence of Adversarial Training	8
Random Multitype Spanning Forests for Synchronization on Sparse Graphs	8
The Geometric Median and Applications to Robust Mean Estimation	7
Numerical Considerations and a new implementation for invariant coordinate selection	7
ABBA Neural Networks: Coping with Positivity, Expressivity, and Robustness	7
Finite-Time Analysis of Natural Actor-Critic for POMDPs	7
Optimal Dorfman Group Testing for Symmetric Distributions	7
Efficient Identification of Butterfly Sparse Matrix Factorizations	7
Benefit of Interpolation in Nearest Neighbor Algorithms	7
Supervised Gromov–Wasserstein Optimal Transport with Metric-Preserving Constraints	7
LASSO Reloaded: A Variational Analysis Perspective with Applications to Compressed Sensing	6
Operator Shifting for General Noisy Matrix Systems	6
Computing Wasserstein Barycenters via Operator Splitting: The Method of Averaged Marginals	6
Post-training Quantization for Neural Networks with Provable Guarantees	6
HADES: Fast Singularity Detection with Local Measure Comparison	5
Complete and Continuous Invariants of 1-Periodic Sequences in Polynomial Time	5
Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning	5
Adaptive Joint Distribution Learning	5
Memory Capacity of Two Layer Neural Networks with Smooth Activations	5
KL Convergence Guarantees for Score Diffusion Models under Minimal Data Assumptions	5
Sequential Construction and Dimension Reduction of Gaussian Processes Under Inequality Constraints	5
Phase Retrieval with Semialgebraic and ReLU Neural Network Priors	5
Multifidelity Covariance Estimation via Regression on the Manifold of Symmetric Positive Definite Matrices	4
Fast Kernel Summation in High Dimensions via Slicing and Fourier Transforms	4
Spectral Properties of Elementwise-Transformed Spiked Matrices	4
Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks	4
Convergence of a Constrained Vector Extrapolation Scheme	4
Stochastic Gradient Descent for Streaming Linear and Rectified Linear Systems with Adversarial Corruptions	4
Accelerated and Instance-Optimal Policy Evaluation with Linear Function Approximation	4
Stability of Sequential Lateration and of Stress Minimization in the Presence of Noise	4
Insights into Kernel PCA with Application to Multivariate Extremes	3
Nonlinear Weighted Directed Acyclic Graph and A Priori Estimates for Neural Networks	3
Simple Alternating Minimization Provably Solves Complete Dictionary Learning	3
Optimization on Manifolds via Graph Gaussian Processes	3
Approximate Q Learning for Controlled Diffusion Processes and Its Near Optimality	3
Approximating Probability Distributions by Using Wasserstein Generative Adversarial Networks	3
The Common Intuition to Transfer Learning Can Win or Lose: Case Studies for Linear Regression	3

First-Order Conditions for Optimization in the Wasserstein Space	3
Ensemble Linear Interpolators: The Role of Ensembling	3
Network Online Change Point Localization	3
Causal Structural Learning via Local Graphs	3
Diffeomorphic Measure Matching with Kernels for Generative Modeling	3
Robust Reinforcement Learning with Dynamic Distortion Risk Measures	3
Efficiency of ETA Prediction	3
Exploring Variance Reduction in Importance Sampling for Efficient DNN Training	3
On the Rates of Convergence for Learning with Convolutional Neural Networks	3
Entropic Optimal Transport on Random Graphs	3
Lipschitz-Regularized Gradient Flows and Generative Particle Algorithms for High-Dimensional Scarce Data	3
Approximate Message Passing with Rigorous Guarantees for Pooled Data and Quantitative Group Testing	3
$k$-Variance: A Clustered Notion of Variance	3
A Priori Estimates for Deep Residual Network in Continuous-Time Reinforcement Learning	3
An Adaptively Inexact First-Order Method for Bilevel Optimization with Application to Hyperparameter Learning	3
Stochastic Optimal Transport in Banach Spaces for Regularized Estimation of Multivariate Quantiles	3
Faster Rates for Compressed Federated Learning with Client-Variance Reduction	2
Landmark Alternating Diffusion	2
Wasserstein-Based Projections with Applications to Inverse Problems	2
Fredholm Integral Equations for Function Approximation and the Training of Neural Networks	2
The Positivity of the Neural Tangent Kernel	2
Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing	2
Optimally Weighted PCA for High-Dimensional Heteroscedastic Data	2
Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks	2
Estimating a Potential Without the Agony of the Partition Function	2
On the Nonconvexity of Push-Forward Constraints and Its Consequences in Machine Learning	2
Determinantal Point Processes Implicitly Regularize Semiparametric Regression Problems	2
On Design of Polyhedral Estimates in Linear Inverse Problems	2
Enforcing Katz and PageRank Centrality Measures in Complex Networks	2
Applications of No-Collision Transportation Maps in Manifold Learning	2
${O({k})}$-Equivariant Dimensionality Reduction on Stiefel Manifolds	2
Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition	2
Online MCMC Thinning with Kernelized Stein Discrepancy	2
Randomly Initialized Alternating Least Squares: Fast Convergence for Matrix Sensing	2
Energy-Based Sequential Sampling for Low-Rank PSD-Matrix Approximation	2
Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations	2
Accelerated Bregman Primal-Dual Methods Applied to Optimal Transport and Wasserstein Barycenter Problems	2